© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113244
    Prev
    Next
    INDEX
    Explanations

    danksharding, dark humor, da qing

    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
    т
    1.45
    ت
    1.41
    л
    1.34
    ب
    1.33
    一
    1.25
    ل
    1.18
    트
    1.17
    ル
    1.12
    ט
    1.08
    ف
    1.02
    POSITIVE LOGITS
     (
    0.99
     in
    0.86
     indag
    0.82
     incentiv
    0.79
    a
    0.79
     invalid
    0.77
     direccion
    0.76
     في
    0.76
     erkennt
    0.74
     חש
    0.71
    Activations Density 0.000%

    No Known Activations