© 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. 12780
    Prev
    Next
    INDEX
    Explanations

    the word "can" and words and punctuation in its immediate context

    oai_token-act-pair · gemini-2.0-flash

    can

    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
     ProtoMessage
    -0.89
    出版年
    -0.80
    iNdEx
    -0.75
    DeleteBehavior
    -0.73
     Efq
    -0.71
    AutoresizingMask
    -0.69
    HandlerContext
    -0.69
     Monfieur
    -0.68
    SharedDtor
    -0.67
    DockStyle
    -0.66
    POSITIVE LOGITS
     Walk
    0.50
    walk
    0.48
     walk
    0.46
    Walk
    0.46
    daille
    0.45
     appré
    0.44
     Lure
    0.44
    GetBytes
    0.42
    werfen
    0.41
     cura
    0.41
    Activations Density 1.574%

    No Known Activations