© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9319
    Prev
    Next
    INDEX
    Explanations

    Java code and documentation, especially related to data types like Integer, Long, and Double, and concepts like hash codes and object conversion.

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or concepts

    np_token-act-pair-logits · gpt-4o-mini

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.66
    出版年
    -0.60
     jsPsych
    -0.59
    Personendaten
    -0.57
    )\}
    -0.56
    stateProvider
    -0.54
    purposes
    -0.53
    исленность
    -0.52
     ModelExpression
    -0.51
     firebaseConfig
    -0.51
    POSITIVE LOGITS
    +#+
    0.54
    come
    0.53
    licone
    0.52
     Vergleich
    0.52
    cile
    0.52
     مرئيه
    0.51
    XmlAccessorType
    0.51
     MonoBehaviour
    0.50
    compare
    0.49
    /*
    0.48
    Activations Density 1.956%

    No Known Activations