© 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. 40779
    Prev
    Next
    INDEX
    Explanations

    superseded by

    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
    t
    0.80
    ।
    0.75
    st
    0.73
    },
    0.71
    }+
    0.68
    ט
    0.68
    ;
    0.66
    of
    0.65
    }
    0.65
     Operation
    0.64
    POSITIVE LOGITS
    ஸ்
    0.73
    uré
    0.72
     organizações
    0.71
    니다
    0.70
    엣
    0.68
    ́c
    0.67
    ንግ
    0.66
     ομά
    0.66
     ہوگی
    0.65
    uram
    0.65
    Activations Density 0.001%

    No Known Activations