© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199704
    Prev
    Next
    INDEX
    Explanations

    *mean* it

    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_12_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
    .*
    0.29
    winged
    0.27
    sah
    0.27
    ningar
    0.27
    tig
    0.27
    trong
    0.27
    sing
    0.26
    grains
    0.26
    biggl
    0.26
    fak
    0.26
    POSITIVE LOGITS
     vendita
    0.31
     recuerda
    0.30
     Queste
    0.30
     ไอ้
    0.30
     Recursos
    0.29
    <0x80>
    0.29
     culp
    0.29
     McDermott
    0.28
    '
    0.28
     murderous
    0.28
    Activations Density 0.001%

    No Known Activations