© 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. 450
    Prev
    Next
    INDEX
    Explanations

    HTML code and surrounding text

    oai_token-act-pair · gemini-2.0-flash

    html

    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
    dev
    -0.48
    chou
    -0.46
    раз
    -0.46
    h
    -0.45
     referrerpolicy
    -0.45
     đ
    -0.45
    gefü
    -0.44
    เป
    -0.44
     should
    -0.43
    fü
    -0.43
    POSITIVE LOGITS
    featureID
    0.82
    UserScript
    0.78
     AssemblyCulture
    0.72
    FTFY
    0.71
     &___
    0.71
     متعلقه
    0.69
     <<=
    0.67
     beginnetje
    0.66
     Roskov
    0.65
     سكانية
    0.63
    Activations Density 1.746%

    No Known Activations