© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215798
    Prev
    Next
    INDEX
    Explanations

    that are

    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_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    d
    1.40
    .
    1.13
    1.06
    ne
    1.05
    स
    1.01
    ہ
    1.00
    บ
    1.00
    স
    0.98
    。
    0.95
     at
    0.94
    POSITIVE LOGITS
    و
    1.27
    ere
    1.25
    你
    1.25
    ot
    1.23
    ens
    1.17
    and
    1.10
    into
    1.10
    ow
    1.09
    ’
    1.09
    out
    1.08
    Activations Density 0.000%

    No Known Activations