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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15411
    Prev
    Next
    INDEX
    Explanations

    the word "game" and related words, in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    game

    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
    Tembelea
    -0.45
     Pristupljeno
    -0.43
     którzy
    -0.42
     ziyaret
    -0.42
     gümüş
    -0.37
    Código
    -0.37
    G
    -0.37
    üe
    -0.36
    SequentialGroup
    -0.35
    iped
    -0.35
    POSITIVE LOGITS
    addCriterion
    0.88
    WebVitals
    0.71
    +#+#
    0.70
    findpost
    0.69
    ThroughAttribute
    0.68
    XmlAccessType
    0.65
     Signalez
    0.65
    Życiorys
    0.65
    ArgsConstructor
    0.65
     lenker
    0.65
    Activations Density 13.400%

    No Known Activations