© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12786
    Prev
    Next
    INDEX
    Explanations

    cardinal directions and geopolitical terms

    oai_token-act-pair · gemini-2.0-flash

    compass directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    initComponents
    -0.56
     TextInputType
    -0.50
    Hochspringen
    -0.49
    المناصب
    -0.49
     BitmapFactory
    -0.48
     termica
    -0.48
     northward
    -0.46
     north
    -0.46
    rubin
    -0.46
     skydd
    -0.45
    POSITIVE LOGITS
    en
    0.63
    }}}{
    0.58
    turn
    0.57
    )}}{
    0.57
    yntaxException
    0.53
    InSection
    0.53
     Turn
    0.52
     pase
    0.52
    DoubleQuotes
    0.52
    ))){
    0.50
    Activations Density 5.886%

    No Known Activations