© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3424
    Prev
    Next
    INDEX
    Explanations

    opinions and discussions about video games

    oai_token-act-pair · gemini-2.0-flash

    video games

    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
     oprot
    -0.46
     kê
    -0.46
    _,
    -0.46
     timeval
    -0.43
    pert
    -0.43
     Chwiliwch
    -0.43
    исленность
    -0.41
     díg
    -0.41
    QMetaType
    -0.40
     teatr
    -0.40
    POSITIVE LOGITS
     createSlice
    0.64
    skjaer
    0.60
    CompilerServices
    0.57
    AFTA
    0.57
    prefixer
    0.56
    <?
    0.56
    reportWebVitals
    0.56
    DockStyle
    0.56
    pulumi
    0.56
     Criterion
    0.55
    Activations Density 8.999%

    No Known Activations