© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9803
    Prev
    Next
    INDEX
    Explanations

    references to parts of a competition, like 'first', 'second', or 'half'

    oai_token-act-pair · gemini-2.0-flash

    game periods

    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
    expandindo
    -0.95
     فريبيس
    -0.94
    AccessorTable
    -0.88
    ViewFeatures
    -0.85
    Geplaatst
    -0.84
     nakalista
    -0.81
     cherchés
    -0.79
    ConstraintMaker
    -0.78
    PMailer
    -0.75
     Administrativna
    -0.73
    POSITIVE LOGITS
     Ro
    0.46
     twenty
    0.44
    TryGetValue
    0.43
     bi
    0.42
     b
    0.42
     #{
    0.41
    #{
    0.41
    وة
    0.40
    าว
    0.40
     neu
    0.40
    Activations Density 0.422%

    No Known Activations