© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35450
    Prev
    Next
    INDEX
    Explanations

    letter options closing parenthesis

    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_31_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
     меньше
    0.37
     lesser
    0.35
    Transaksi
    0.34
    逐渐
    0.34
     постепенно
    0.34
    厷
    0.34
     tady
    0.33
     smaller
    0.33
    班
    0.33
    Հ
    0.33
    POSITIVE LOGITS
     interests
    0.35
     Greenberg
    0.35
    仕組み
    0.35
     Wol
    0.34
     intérêts
    0.34
    }={\
    0.34
    PropTypes
    0.33
    sect
    0.33
     Adverse
    0.33
    paired
    0.33
    Activations Density 0.002%

    No Known Activations