© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101472
    Prev
    Next
    INDEX
    Explanations

    being polite, dumped, wanted

    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_16_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
     serializer
    0.30
    serializer
    0.28
     mostr
    0.28
    耶路撒
    0.28
    üp
    0.28
     WHILE
    0.28
    ুইস
    0.28
    ﻥ
    0.27
     effectiveness
    0.26
     चिह्न
    0.26
    POSITIVE LOGITS
    ('
    0.36
    "/
    0.35
    /
    0.32
    াযোগ
    0.31
     Rojo
    0.30
    _{\
    0.30
    ('.')[
    0.30
     Duniya
    0.29
    Э
    0.29
     plant
    0.29
    Activations Density 0.027%

    No Known Activations