© 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. 228193
    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
    in
    1.05
    H
    0.95
    K
    0.91
    T
    0.90
    A
    0.89
    E
    0.88
    ک
    0.86
    V
    0.85
    க
    0.85
    S
    0.85
    POSITIVE LOGITS
    ấu
    0.59
     lång
    0.56
     refinance
    0.56
     lí
    0.54
     ér
    0.53
     đẩy
    0.52
     бас
    0.52
     bài
    0.52
     valeurs
    0.52
     ONT
    0.52
    Activations Density 0.000%

    No Known Activations