© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11888
    Prev
    Next
    INDEX
    Explanations

    shift changes

    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_40_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
     الاحت
    0.38
    Ỏ
    0.35
     स्क्वायर
    0.35
    ฬา
    0.34
    }&=
    0.34
     Dutton
    0.33
    WV
    0.33
    糉
    0.33
    cretsiz
    0.33
    鿓
    0.33
    POSITIVE LOGITS
     shift
    2.77
    shift
    2.52
     shifts
    2.45
     Shift
    2.42
    Shift
    2.33
    shifts
    2.20
     Shifts
    2.20
    シフト
    2.11
     shifted
    1.98
    SHIFT
    1.94
    Activations Density 0.063%

    No Known Activations