© 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. 198488
    Prev
    Next
    INDEX
    Explanations

    audi A4

    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
    let
    0.37
    ；
    0.37
    doc
    0.35
    le
    0.34
    dmg
    0.34
     ;)
    0.34
    ளம்
    0.34
    dh
    0.33
    n
    0.33
    chat
    0.33
    POSITIVE LOGITS
    กีฬา
    0.35
     illustrates
    0.33
     Sculpture
    0.32
    യില്ല
    0.32
     HENRY
    0.32
     wasnt
    0.30
     cahaya
    0.30
    磴
    0.30
    вання
    0.30
     sculpture
    0.30
    Activations Density 0.000%

    No Known Activations