© 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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 456
    Prev
    Next
    INDEX
    Explanations

    code snippets, file operations and birthday wishes

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    InjectAttribute
    -0.91
     InputDecoration
    -0.91
    providedIn
    -0.85
    Portale
    -0.76
    ViewFeatures
    -0.75
     للاسماء
    -0.74
     تضيفلها
    -0.74
    reactstrap
    -0.74
    GraphicsUnit
    -0.74
    ScopeManager
    -0.74
    POSITIVE LOGITS
    🎰
    0.48
     beggar
    0.45
     nødven
    0.45
    kri
    0.43
    <bos>
    0.42
     odp
    0.41
     silencio
    0.40
     ansatte
    0.40
    кри
    0.40
    esthes
    0.40
    Activations Density 64.080%

    No Known Activations