© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198888
    Prev
    Next
    INDEX
    Explanations

    era, planet, Mac

    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_4_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
    在
    0.56
     في
    0.56
     glaub
    0.51
    ský
    0.48
    č
    0.48
    ská
    0.47
    zés
    0.47
    zeit
    0.47
     quell
    0.47
     größ
    0.47
    POSITIVE LOGITS
    is
    0.82
    ะ
    0.70
    ای
    0.65
    ח
    0.64
    and
    0.60
    ק
    0.57
    نا
    0.57
    اک
    0.55
    of
    0.54
    ート
    0.54
    Activations Density 0.001%

    No Known Activations