© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29757
    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_10_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
    _
    0.56
    ار
    0.52
     direktor
    0.52
    V
    0.49
    ن
    0.49
     komb
    0.48
     my
    0.48
     delle
    0.48
     vintage
    0.47
    К
    0.47
    POSITIVE LOGITS
    gah
    0.52
     overwhelmingly
    0.51
     messageFields
    0.48
    constraintlayout
    0.46
    RowFilter
    0.46
    TabData
    0.44
     характер
    0.44
    <unused2184>
    0.44
    determined
    0.43
     அங்க
    0.43
    Activations Density 0.000%

    No Known Activations