© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1493
    Prev
    Next
    INDEX
    Explanations

    code snippets with keywords such as 'if', 'return', and parenthesis

    oai_token-act-pair · gemini-2.0-flash

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ekt
    -0.41
     ويكيميديا
    -0.40
    故
    -0.40
    (&:
    -0.39
     аппетита
    -0.38
     lateinit
    -0.38
    šče
    -0.38
    refs
    -0.37
    Gleich
    -0.36
    🏽
    -0.36
    POSITIVE LOGITS
     nahilalakip
    0.81
    numerusform
    0.75
     transfieras
    0.67
     يتيمه
    0.67
    bootstrapcdn
    0.66
    بوابة
    0.66
    withIdentifier
    0.63
    DataURL
    0.63
    AntiForgeryToken
    0.62
    出版年
    0.62
    Activations Density 20.288%

    No Known Activations