© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9355
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of Japanese greetings, anatomy and technical invention-related terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    は
    -1.25
     は
    -1.03
    은
    -0.95
    는
    -0.94
    <bos>
    -0.85
    も
    -0.80
    さんは
    -0.73
    はお
    -0.72
    には
    -0.71
    氏は
    -0.71
    POSITIVE LOGITS
     MainAxisSize
    0.66
     kaarangay
    0.63
     AssemblyCulture
    0.61
     rowspan
    0.59
     Roskov
    0.59
     cytok
    0.59
    shadowRadius
    0.56
    ագրություններ
    0.55
    greatest
    0.53
    ()];
    0.52
    Activations Density 0.683%

    No Known Activations