© 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. 14182
    Prev
    Next
    INDEX
    Explanations

    the prefix "sur"

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'Sur'

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

    sur

    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
     AssemblyTitle
    -0.66
    webElement
    -0.63
    MENAFN
    -0.62
     समीक्षक
    -0.62
     ModelExpression
    -0.61
    DeleteBehavior
    -0.61
    PerformLayout
    -0.60
    IANGLES
    -0.60
    Sucesor
    -0.60
     Biôgrafia
    -0.59
    POSITIVE LOGITS
     fa
    0.48
    strö
    0.47
     plotting
    0.47
     FAC
    0.46
     androidx
    0.46
    Plo
    0.46
     acetate
    0.45
     rounding
    0.44
     Acetate
    0.43
    RenderAtEndOf
    0.42
    Activations Density 0.279%

    No Known Activations