© 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. 4970
    Prev
    Next
    INDEX
    Explanations

    legal citations, references, and terminology

    oai_token-act-pair · gemini-2.0-flash

    Legal/financial documents

    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
    DockStyle
    -1.03
    MigrationBuilder
    -0.94
    Personendaten
    -0.90
     للاسماء
    -0.88
    providedIn
    -0.88
     تضيفلها
    -0.84
     kaynağından
    -0.83
    SourceChecksum
    -0.82
     Signalez
    -0.77
     unknownFields
    -0.77
    POSITIVE LOGITS
    9
    0.44
    loroethane
    0.42
     تانيه
    0.39
    还有一
    0.38
    tauscht
    0.37
    E
    0.36
    шеб
    0.34
    DOWN
    0.33
    down
    0.33
    allage
    0.33
    Activations Density 52.021%

    No Known Activations