© 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. 8383
    Prev
    Next
    INDEX
    Explanations

    suggestions and advice

    oai_token-act-pair · gemini-2.0-flash

    uncertainty

    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
    ########.
    -0.78
     Shakspeare
    -0.60
     Cæsar
    -0.57
     Shaksp
    -0.56
     cheapest
    -0.56
     prerequisite
    -0.56
     umbi
    -0.54
     precedence
    -0.53
    Искәрмәләр
    -0.53
     safest
    -0.53
    POSITIVE LOGITS
     perhaps
    0.97
     maybe
    0.94
    perhaps
    0.87
     might
    0.85
     Perhaps
    0.83
    maybe
    0.82
     may
    0.78
    Perhaps
    0.77
     možná
    0.76
     quizás
    0.75
    Activations Density 2.613%

    No Known Activations