© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57967
    Prev
    Next
    INDEX
    Explanations

    CW, CCW, UFCW, RawÇW

    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_2_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
    ون
    1.40
    는
    1.36
    am
    1.30
    d
    1.26
    ib
    1.15
    は
    1.12
    ።
    1.10
    ۔
    1.09
     जिसके
    1.08
    lade
    1.06
    POSITIVE LOGITS
    ва
    1.48
    ’
    1.41
     It
    1.09
    са
    0.98
    is
    0.97
     phare
    0.95
    ⁃
    0.93
    ＇
    0.88
     There
    0.88
     broni
    0.86
    Activations Density 0.000%

    No Known Activations