© 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. 231935
    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
    s
    1.43
    3
    1.23
    in
    1.20
    1
    1.09
    ’
    1.07
    ha
    1.06
    5
    1.06
    ים
    1.05
    6
    1.05
    ↵↵
    1.02
    POSITIVE LOGITS
    <0x80>
    1.13
    н
    0.90
    ндо
    0.87
    ن
    0.87
    ي
    0.84
    ل
    0.83
     majeure
    0.83
    ли
    0.82
    며
    0.81
     музыки
    0.81
    Activations Density 0.000%

    No Known Activations