© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11512
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to sports, entertainment, and general determiners and prepositions

    oai_token-act-pair · gemini-2.0-flash

    act

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    FormState
    -0.65
     poveznice
    -0.54
     ioutil
    -0.54
     riuscito
    -0.53
     nascita
    -0.52
     חיצוניים
    -0.51
    Kjelder
    -0.51
     שוליים
    -0.51
     xrange
    -0.51
     relatifs
    -0.50
    POSITIVE LOGITS
     act
    2.58
     Act
    1.94
    act
    1.85
     acts
    1.81
    Act
    1.73
     Acts
    1.37
     acted
    1.31
    acts
    1.30
     ACT
    1.26
    Acts
    1.23
    Activations Density 2.212%

    No Known Activations