© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84456
    Prev
    Next
    INDEX
    Explanations

    Chinese and Russian names/titles

    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_0_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
    g
    1.82
    AY
    1.52
    p
    1.46
    F
    1.30
     is
    1.27
    O
    1.26
    8
    1.24
    ركة
    1.22
    H
    1.18
     تي
    1.16
    POSITIVE LOGITS
    นี้
    1.59
    이다
    1.54
    ก็
    1.43
    </h2>
    1.30
    も
    1.30
     a
    1.29
    こと
    1.27
    으로
    1.23
    ไม่ใช่
    1.22
    ется
    1.21
    Activations Density 0.000%

    No Known Activations