© 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. 288
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and licensing information, particularly those related to software

    oai_token-act-pair · gemini-2.0-flash

    FITNESS

    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
    AndEndTag
    -0.46
    ViewImports
    -0.41
    \{\\
    -0.36
     houſe
    -0.33
     myſelf
    -0.33
    GraphicsUnit
    -0.32
     purpoſe
    -0.32
     ſtate
    -0.31
     raiſ
    -0.31
    LayoutPanel
    -0.31
    POSITIVE LOGITS
    <bos>
    0.66
     cherchés
    0.49
     мәкал
    0.46
     ویکی‌پدی
    0.44
     orari
    0.43
     Intelligen
    0.43
     ModelExpression
    0.42
     validamos
    0.42
     oprot
    0.41
     NgModule
    0.41
    Activations Density 0.695%

    No Known Activations