© 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. 184109
    Prev
    Next
    INDEX
    Explanations

    Magneto

    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
     managers
    0.36
    Comma
    0.34
    ారా
    0.32
    MDA
    0.32
    ুয়ার
    0.30
     bombas
    0.30
    Mar
    0.29
    தூ
    0.29
    拷
    0.29
     bureaucr
    0.29
    POSITIVE LOGITS
    <<<<
    0.33
    <<"
    0.32
    献
    0.32
    ]))
    0.32
     "<<
    0.31
    <<
    0.31
     ]))
    0.30
    畊
    0.30
     understated
    0.30
    balanced
    0.30
    Activations Density 0.007%

    No Known Activations