© 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. 80034
    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
    ו
    1.82
    the
    1.78
    re
    1.77
    sthe
    1.60
    t
    1.59
    is
    1.57
    m
    1.52
    on
    1.41
    و
    1.40
    z
    1.39
    POSITIVE LOGITS
    ?
    1.77
    е
    1.64
    רו
    1.62
    ור
    1.55
    0
    1.55
    !
    1.39
    ח
    1.30
    ',
    1.30
    ।
    1.28
    ка
    1.25
    Activations Density 0.000%

    No Known Activations