© 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. 45962
    Prev
    Next
    INDEX
    Explanations

    %

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    8
    0.46
    CH
    0.44
     at
    0.44
    out
    0.43
     an
    0.43
    </h2>
    0.42
    one
    0.41
     for
    0.41
    Ch
    0.41
    at
    0.39
    POSITIVE LOGITS
    ем
    0.39
     vattum
    0.39
    劦
    0.39
     stature
    0.37
    zám
    0.35
    荕
    0.35
    iség
    0.35
     diminution
    0.34
     velocità
    0.34
     discrep
    0.34
    Activations Density 0.052%

    No Known Activations