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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12943
    Prev
    Next
    INDEX
    Explanations

    numerical data related to sports scores, dates, and measurements

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    χυ
    -0.75
    Portale
    -0.74
    帖最后由
    -0.64
    numerusform
    -0.63
     freezes
    -0.63
    verages
    -0.62
    LLocation
    -0.62
    ثيق
    -0.62
    rawDesc
    -0.62
    REQUIRES
    -0.61
    POSITIVE LOGITS
    <bos>
    0.85
     BoxDecoration
    0.49
    WireFormat
    0.49
    2
    0.48
    You
    0.47
    6
    0.46
     gomma
    0.45
    All
    0.45
    bar
    0.43
    is
    0.42
    Activations Density 8.836%

    No Known Activations