© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13104
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, percentages, and rates

    oai_token-act-pair · gemini-2.0-flash

    quantifiable metrics

    np_token-act-pair-logits · gpt-4o-mini

    percentage points

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AssemblyCulture
    -0.91
     AssemblyProduct
    -0.70
     الرياضيه
    -0.63
     houſe
    -0.60
     صوتيه
    -0.59
    CodeAttribute
    -0.57
     للمعارف
    -0.57
    gdx
    -0.56
     ſtill
    -0.54
     ſtate
    -0.53
    POSITIVE LOGITS
     points
    1.14
     percentage
    1.12
     point
    1.02
    points
    1.00
    percentage
    0.97
    point
    0.96
     Points
    0.95
     POINTS
    0.91
    Points
    0.90
    Point
    0.89
    Activations Density 2.660%

    No Known Activations