© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105638
    Prev
    Next
    INDEX
    Explanations

    obstacles

    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
    3
    1.15
    <0x80>
    1.07
    ﻦ
    1.01
    6
    0.98
    ม
    0.96
     vidé
    0.95
    m
    0.93
    4
    0.92
    elijke
    0.89
    il
    0.88
    POSITIVE LOGITS
    ה
    1.19
    も含
    1.08
    も
    1.06
    이었
    1.02
    ので
    0.95
    取り
    0.94
     infidelity
    0.93
    ם
    0.93
    ’
    0.92
     in
    0.91
    Activations Density 0.001%

    No Known Activations