© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83940
    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_0_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
    나
    1.41
    ט
    1.22
    чности
    1.21
    多く
    1.20
    ्युअर
    1.17
    ۲
    1.13
    ות
    1.12
    高く
    1.11
    ್ಟ
    1.10
    кових
    1.10
    POSITIVE LOGITS
    ه
    1.74
    l
    1.67
    a
    1.66
    .
    1.53
    '
    1.48
     de
    1.33
    to
    1.33
    1
    1.32
    ka
    1.31
     in
    1.29
    Activations Density 0.000%

    No Known Activations