© 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-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232128
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    1.16
    ı
    1.08
    ale
    1.02
    ’
    1.02
    av
    0.97
    ata
    0.95
    id
    0.95
    up
    0.93
    uk
    0.93
    I
    0.93
    POSITIVE LOGITS
    تون
    0.90
    лон
    0.85
    <0x8A>
    0.83
    <0x8C>
    0.82
    <0x8F>
    0.79
     সচিব
    0.78
    ،
    0.78
    форд
    0.77
    <0xA2>
    0.75
    вера
    0.75
    Activations Density 0.000%

    No Known Activations