© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12855
    Prev
    Next
    INDEX
    Explanations

    instances where someone is thinking or attempting to perform an action

    oai_token-act-pair · gemini-2.0-flash

    computer actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    featureID
    -0.97
    MarshalTo
    -0.75
     Мексичка
    -0.72
     ddelweddau
    -0.69
     transférez
    -0.68
    aarrggbb
    -0.66
    WithFormat
    -0.66
    HandlerContext
    -0.66
    ContextHolder
    -0.64
    
    -0.64
    POSITIVE LOGITS
    '
    0.44
     Leicht
    0.42
     pression
    0.41
    季
    0.41
    Title
    0.41
    Untitled
    0.39
    Albert
    0.39
    my
    0.39
    --
    0.39
    invalidate
    0.39
    Activations Density 0.898%

    No Known Activations