© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15936
    Prev
    Next
    INDEX
    Explanations

    sentences or questions in French using "je" (I) and second person conjugations

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     propOrder
    -0.90
     could
    -0.77
     pleaſure
    -0.77
    EndInit
    -0.76
     ModelExpression
    -0.75
     typelib
    -0.72
     تضيفلها
    -0.70
     ſhe
    -0.69
    SharedCtor
    -0.69
     ProtoMessage
    -0.68
    POSITIVE LOGITS
     can
    0.94
    can
    0.79
     Can
    0.79
    Can
    0.73
    CAN
    0.71
    cana
    0.63
     CAN
    0.56
     Cant
    0.52
    ecan
    0.50
     kan
    0.48
    Activations Density 0.890%

    No Known Activations