© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177444
    Prev
    Next
    INDEX
    Explanations

    sensitive topics or explicit content

    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_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     deceive
    0.45
     simple
    0.40
     SIMPLE
    0.39
    ง่าย
    0.39
    ರ್ಥ
    0.39
    費
    0.38
     PUN
    0.38
     scattered
    0.37
    뭅
    0.37
     simples
    0.36
    POSITIVE LOGITS
     Tradu
    0.40
     unthinkable
    0.39
     audacious
    0.37
     embarrassing
    0.36
    labelledby
    0.35
    translations
    0.35
     Historically
    0.35
    ాల్సి
    0.35
    antera
    0.35
     translated
    0.35
    Activations Density 0.071%

    No Known Activations