© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135300
    Prev
    Next
    INDEX
    Explanations

    that now

    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_1_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
    es
    1.52
    as
    1.48
    os
    1.41
    on
    1.38
    H
    1.38
    A
    1.19
    ut
    1.17
    ak
    1.16
    an
    1.15
    ι
    1.14
    POSITIVE LOGITS
     that
    0.95
     for
    0.92
     won
    0.91
     <=
    0.90
    )]
    0.86
    ]
    0.85
     with
    0.83
     THEY
    0.82
    )
    0.80
     DON
    0.80
    Activations Density 0.001%

    No Known Activations