© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 710
    Prev
    Next
    INDEX
    Explanations

    statements about behavior, especially when unexpected or related to code.

    oai_token-act-pair · gemini-2.0-flash

    behave

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     useDispatch
    -0.57
    __).
    -0.52
    zyści
    -0.51
     estekak
    -0.49
    łada
    -0.49
     vorstellen
    -0.48
     المعيارى
    -0.48
    */),
    -0.47
     AssemblyProduct
    -0.44
     szer
    -0.44
    POSITIVE LOGITS
     behavior
    2.22
     behaviour
    2.03
     Behavior
    1.92
    behavior
    1.84
     comportement
    1.78
    Behavior
    1.77
     BEHAVIOR
    1.73
     BEHAV
    1.70
     behaviors
    1.70
     Behaviour
    1.69
    Activations Density 3.003%

    No Known Activations