© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33301
    Prev
    Next
    INDEX
    Explanations

    Commander-in-Chief

    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_7_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
    as
    1.13
    al
    1.11
    es
    0.99
    ل
    0.99
    ق
    0.98
    ות
    0.95
    ad
    0.95
    ب
    0.87
    u
    0.85
    c
    0.84
    POSITIVE LOGITS
    ’
    0.80
    4
    0.79
    </h2>
    0.78
    یر
    0.76
     pouring
    0.75
    ﯽ
    0.71
    Pour
    0.71
    ﻤ
    0.70
    </h1>
    0.68
    ﾟ
    0.68
    Activations Density 0.001%

    No Known Activations