© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133798
    Prev
    Next
    INDEX
    Explanations

    past events and periods

    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_1_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
    ت
    1.48
     was
    1.45
    {
    1.27
    A
    1.26
    a
    1.23
    i
    1.16
     has
    1.15
    ي
    1.15
     {
    1.12
    त
    1.11
    POSITIVE LOGITS
    ной
    0.97
    ної
    0.96
    čkog
    0.89
    가가
    0.88
    ﻀ
    0.87
    ées
    0.86
    ना
    0.86
    ный
    0.86
    ﺼ
    0.86
    ното
    0.84
    Activations Density 0.001%

    No Known Activations