© 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. 45467
    Prev
    Next
    INDEX
    Explanations

    overview

    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
    iad
    0.67
    i
    0.60
    ت
    0.57
    ों
    0.55
    s
    0.54
    يس
    0.54
     Danish
    0.51
     for
    0.51
     Php
    0.51
    ບບ
    0.51
    POSITIVE LOGITS
    प
    0.62
     stadiums
    0.60
    ப
    0.59
    ש
    0.58
    ル
    0.57
     sobie
    0.56
    ścic
    0.56
    時間に
    0.55
    は
    0.55
     تبدی
    0.54
    Activations Density 0.000%

    No Known Activations