© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103992
    Prev
    Next
    INDEX
    Explanations

    overhead press

    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_1_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
    ۴
    1.61
    ۶
    1.34
    ला
    1.31
    ۵
    1.30
    る
    1.27
    action
    1.23
    year
    1.20
    ৬
    1.20
    oc
    1.20
    c
    1.20
    POSITIVE LOGITS
    i
    1.38
    ة
    1.18
     Schrödinger
    1.05
     možnosti
    1.01
    ing
    1.00
     μεγάλη
    0.97
    స్కీ
    0.94
     mögliche
    0.94
     interação
    0.93
     Möbius
    0.93
    Activations Density 0.001%

    No Known Activations