© 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. 5618
    Prev
    Next
    INDEX
    Explanations

    references to research studies and statistical data with a focus on drugs, alcohol and race.

    oai_token-act-pair · gemini-2.0-flash

    Demographics and statistics

    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
     архивлан
    -0.65
    sizeCache
    -0.61
    Predecesor
    -0.59
    ListItemIcon
    -0.57
    RetentionPolicy
    -0.57
     linkovi
    -0.56
    IBOutlet
    -0.55
    disposing
    -0.55
    TypedDataSet
    -0.53
    InitStruct
    -0.53
    POSITIVE LOGITS
    seamnă
    0.63
    таратура
    0.61
     pronti
    0.57
     '\\;'
    0.56
    θρω
    0.54
    InMillis
    0.50
     pronta
    0.50
     CDF
    0.50
     collects
    0.49
     americanos
    0.48
    Activations Density 1.918%

    No Known Activations