© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51014
    Prev
    Next
    INDEX
    Explanations

    Mostaque, Chow, Hamdan, Mahadictator

    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_10_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
    ING
    0.89
     .
    0.82
    *
    0.76
     "
    0.69
     {
    0.69
    х
    0.65
     for
    0.64
     الكثير
    0.63
    ﻣ
    0.63
    ing
    0.62
    POSITIVE LOGITS
    se
    0.91
    々は
    0.83
    er
    0.77
    f
    0.76
    kan
    0.75
    events
    0.74
    have
    0.73
    sama
    0.72
    h
    0.71
    raw
    0.70
    Activations Density 0.012%

    No Known Activations