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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6987
    Prev
    Next
    INDEX
    Explanations

    words related to the potential or expected future

    oai_token-act-pair · gemini-2.0-flash

    relates to totals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ImageContext
    -0.55
    Close
    -0.54
     ModelExpression
    -0.53
    dame
    -0.49
     Close
    -0.48
    
    -0.47
    콤
    -0.44
     FRAME
    -0.44
    Point
    -0.44
     CLOSE
    -0.43
    POSITIVE LOGITS
     total
    0.81
     unknownFields
    0.69
    total
    0.69
    migrationBuilder
    0.64
     totale
    0.62
    исленность
    0.61
     Total
    0.60
    Total
    0.57
     kiệm
    0.57
    mycin
    0.55
    Activations Density 9.770%

    No Known Activations