Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13430
    Prev
    Next
    INDEX
    Explanations

    words with uncommon character combinations

    oai_token-act-pair · 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
    帖最后由
    -0.81
     समीक्षाओं
    -0.68
     ModelExpression
    -0.68
    Referencie
    -0.66
     المعيارى
    -0.64
    WithIOException
    -0.64
    “…”
    -0.64
     ProtoMessage
    -0.63
    μως
    -0.61
     nahilalakip
    -0.60
    POSITIVE LOGITS
     /\.(
    0.50
    InputBorder
    0.49
     Lehre
    0.47
    atação
    0.45
    Portail
    0.44
    epa
    0.44
    检索
    0.43
    our
    0.43
     resting
    0.42
     /\.
    0.42
    Activations Density 5.057%

    No Known Activations