© 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. 10468
    Prev
    Next
    INDEX
    Explanations

    text relating to open source software

    oai_token-act-pair · gemini-2.0-flash

    open

    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
     متعلقه
    -0.80
    AccessorTable
    -0.78
    DeleteBehavior
    -0.77
     AttributeSet
    -0.73
    featureID
    -0.70
    InjectAttribute
    -0.70
    ViewImports
    -0.69
    rungsseite
    -0.69
     BoxFit
    -0.69
    ymce
    -0.68
    POSITIVE LOGITS
     open
    2.52
    open
    2.09
     Open
    1.95
    Open
    1.93
     OPEN
    1.67
    OPEN
    1.58
     opens
    1.55
     offenen
    1.51
     откры
    1.48
    オープン
    1.48
    Activations Density 3.845%

    No Known Activations