© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10599
    Prev
    Next
    INDEX
    Explanations

    dates and times, sometimes mixed with other metadata like version numbers or abbreviations

    oai_token-act-pair · gemini-2.0-flash

    technical documents or logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    anskje
    -0.48
    IDENTIAL
    -0.46
    หวัด
    -0.45
    legungen
    -0.45
     Schulte
    -0.44
    numbered
    -0.44
     Polres
    -0.43
    unately
    -0.43
    ODER
    -0.43
    Público
    -0.42
    POSITIVE LOGITS
    DockStyle
    0.83
    queryInterface
    0.79
    AndEndTag
    0.76
    脚注の使い方
    0.73
     nakalista
    0.70
     للاسماء
    0.69
    AntiForgeryToken
    0.69
    RegistryLite
    0.68
    adaptiveStyles
    0.68
    unknownFields
    0.67
    Activations Density 5.943%

    No Known Activations