© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14054
    Prev
    Next
    INDEX
    Explanations

    phrases describing agreement with results

    oai_token-act-pair · gemini-2.0-flash

    is or in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    TagMode
    -0.94
    GEBURTSDATUM
    -0.94
     виправивши
    -0.87
     وتسجيلات
    -0.85
     nahilalakip
    -0.84
     lenker
    -0.83
     ModelExpression
    -0.82
     كومونز
    -0.79
     SwitchCompat
    -0.78
    setVerticalGroup
    -0.77
    POSITIVE LOGITS
     in
    1.55
     In
    0.81
    in
    0.81
     в
    0.78
    In
    0.75
     în
    0.71
    ใน
    0.65
     در
    0.61
     في
    0.56
     IN
    0.55
    Activations Density 2.292%

    No Known Activations