© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146243
    Prev
    Next
    INDEX
    Explanations

    LIN, MIN, frist

    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_0_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
    r
    2.14
     (
    2.02
    s
    1.96
    م
    1.69
     It
    1.68
    an
    1.58
    n
    1.55
    L
    1.53
    in
    1.49
    או
    1.45
    POSITIVE LOGITS
    ކ
    1.27
     punctures
    1.27
    ciendo
    1.22
     effluents
    1.22
    ਮ
    1.19
     vendeurs
    1.18
    ри
    1.16
     œuvres
    1.11
     clots
    1.10
    calar
    1.10
    Activations Density 0.000%

    No Known Activations