© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8462
    Prev
    Next
    INDEX
    Explanations

    phrases about ornithology and ecological research

    oai_token-act-pair · gemini-2.0-flash

    Animal behavior

    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
    AntiForgeryToken
    -0.68
     AppBundle
    -0.67
    SourceChecksum
    -0.66
     électro
    -0.61
     GIPHY
    -0.60
    resaid
    -0.60
     BoxFit
    -0.60
    principalColumn
    -0.60
     originais
    -0.59
    myModal
    -0.59
    POSITIVE LOGITS
     Waray
    0.61
     face
    0.57
     cara
    0.50
    Accessors
    0.49
     faced
    0.49
     bando
    0.48
    om
    0.47
     pon
    0.47
    soort
    0.47
     Vor
    0.47
    Activations Density 16.086%

    No Known Activations