© 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. 8728
    Prev
    Next
    INDEX
    Explanations

    legal language related to court proceedings

    oai_token-act-pair · gemini-2.0-flash

    upon

    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
    談社
    -0.55
    untung
    -0.54
    zędu
    -0.49
     slits
    -0.48
    pēc
    -0.48
     allá
    -0.48
     stoneware
    -0.47
     Gillette
    -0.47
    OnEvent
    -0.46
    ControllerAdvice
    -0.46
    POSITIVE LOGITS
    oredCriteria
    0.65
    rungsseite
    0.63
    ThroughAttribute
    0.60
    __*/
    0.60
     occasion
    0.57
    posedge
    0.56
    ьа
    0.56
    expandindo
    0.55
     behalf
    0.53
    ParallelGroup
    0.52
    Activations Density 4.796%

    No Known Activations