© 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. 127268
    Prev
    Next
    INDEX
    Explanations

    Saint-Exupéry, Saint-Rémy, Saint-Cyprien, Polycarp

    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
     be
    0.99
    3
    0.93
    是
    0.87
    ;
    0.86
     of
    0.80
    يد
    0.76
    و
    0.75
    {
    0.74
    \%,
    0.74
    é
    0.74
    POSITIVE LOGITS
    ر
    1.00
    ت
    0.93
    t
    0.90
    نی
    0.82
    یک
    0.80
    رین
    0.80
    ﻡ
    0.80
    ೇ
    0.79
    木の
    0.76
     inglese
    0.75
    Activations Density 0.000%

    No Known Activations