© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104522
    Prev
    Next
    INDEX
    Explanations

    repetitive strings or placeholders

    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
    在
    1.47
    我
    1.29
     যেটি
    1.27
    os
    1.17
    เรา
    1.14
    的做法
    1.09
    కు
    1.07
    س
    1.05
    很多
    1.02
    ના
    1.00
    POSITIVE LOGITS
    ר
    1.95
    ر
    1.63
    to
    1.54
     to
    1.40
    has
    1.37
    r
    1.31
     with
    1.30
     by
    1.29
     shameful
    1.28
    র
    1.23
    Activations Density 0.002%

    No Known Activations