© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205725
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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_25_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
    你有
    0.40
    鏻
    0.38
    vala
    0.37
    你要
    0.37
    imension
    0.36
    候補
    0.36
     desem
    0.36
    čnosti
    0.36
     ఎమ్మె
    0.35
    秞
    0.35
    POSITIVE LOGITS
     transports
    0.39
     barracks
    0.38
    Corps
    0.38
     harbour
    0.38
    Yellow
    0.37
    Qu
    0.37
     Centre
    0.37
     Corps
    0.37
     broad
    0.36
     principalmente
    0.36
    Activations Density 0.010%

    No Known Activations