© 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. 198336
    Prev
    Next
    INDEX
    Explanations

    removal spells

    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
    A
    0.67
    _
    0.56
    1
    0.55
    ...
    0.55
     aurait
    0.54
    </td>
    0.52
    (
    0.52
    R
    0.52
    s
    0.52
    ার
    0.50
    POSITIVE LOGITS
     NCBI
    0.58
     سکے۔
    0.55
    रांत
    0.55
    aparikkh
    0.54
    蘖
    0.54
     médicament
    0.53
     Kharkiv
    0.52
    রোগ
    0.50
     CXCL
    0.50
     CNC
    0.48
    Activations Density 0.000%

    No Known Activations