© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91854
    Prev
    Next
    INDEX
    Explanations

    chase away the shadows

    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_3_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
    1
    0.86
     that
    0.84
    2
    0.81
    י
    0.72
    that
    0.71
     integra
    0.70
    ه
    0.70
    ı
    0.68
    ik
    0.68
    Зна
    0.68
    POSITIVE LOGITS
    اره
    0.71
    ከል
    0.66
    ilus
    0.65
    린
    0.59
    agascar
    0.58
    스러
    0.56
    差
    0.55
    ᅯ
    0.55
    aging
    0.53
    нология
    0.53
    Activations Density 0.001%

    No Known Activations