© 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. 146277
    Prev
    Next
    INDEX
    Explanations

    maps

    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
    ва
    1.88
    м
    1.78
    ii
    1.46
    다
    1.45
    িন
    1.30
     with
    1.27
    ni
    1.24
    ная
    1.24
     it
    1.23
    の問題
    1.23
    POSITIVE LOGITS
    ب
    1.63
    ↵↵
    1.48
    ه
    1.44
    a
    1.35
    al
    1.16
    ు
    1.16
    ти
    1.13
    ंतर
    1.02
    在
    1.02
    中
    1.02
    Activations Density 0.001%

    No Known Activations