© 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. 206426
    Prev
    Next
    INDEX
    Explanations

    oblong shapes and arborists

    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_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
    1.25
    ot
    1.17
    !
    1.08
    be
    1.04
    ene
    1.01
    o
    0.98
    yl
    0.96
    .
    0.93
     about
    0.91
     River
    0.89
    POSITIVE LOGITS
    ב
    1.07
     edificios
    1.01
     дов
    0.96
     bimod
    0.95
    де
    0.95
    ાસ
    0.95
     elems
    0.93
     apporter
    0.91
    И
    0.90
     internationaux
    0.90
    Activations Density 0.000%

    No Known Activations