© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15283
    Prev
    Next
    INDEX
    Explanations

    dates or references to time

    oai_token-act-pair · gemini-2.0-flash

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Efq
    -0.49
    +#+
    -0.48
    :+:
    -0.48
    XmlAccessorType
    -0.45
     GetEnumerator
    -0.44
     nàng
    -0.44
    énario
    -0.44
    IBinder
    -0.43
    начально
    -0.42
    DropColumn
    -0.42
    POSITIVE LOGITS
    MLLoader
    0.62
    RegistryLite
    0.55
     odkazy
    0.54
     jsPsych
    0.51
    öhe
    0.51
     XHTML
    0.51
    CoV
    0.50
    ObjectContext
    0.49
     millas
    0.48
    distan
    0.47
    Activations Density 1.901%

    No Known Activations