© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42226
    Prev
    Next
    INDEX
    Explanations

    Sheesh Mahal or sheesha

    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_3_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
     بیټ
    0.79
    쯜
    0.78
     Oiseau
    0.73
     honti
    0.72
    اتي
    0.71
     freno
    0.71
     regreso
    0.71
     difficol
    0.71
    zovaniyu
    0.71
     atunci
    0.70
    POSITIVE LOGITS
    1
    0.97
     on
    0.90
    the
    0.86
    2
    0.82
    ick
    0.80
    land
    0.80
    sp
    0.79
    de
    0.79
    ten
    0.78
     (
    0.77
    Activations Density 0.000%

    No Known Activations