© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192435
    Prev
    Next
    INDEX
    Explanations

    Guantanamo Bay

    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_4_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
    ي
    0.96
    ".
    0.92
    .";
    0.83
     buildFor
    0.83
    H
    0.81
    ות
    0.80
    ৮
    0.80
    수를
    0.79
    "/>
    0.79
     destac
    0.79
    POSITIVE LOGITS
    s
    1.52
    d
    1.48
    t
    1.31
    y
    1.28
    of
    1.17
    on
    1.09
    g
    1.07
    le
    1.05
    list
    0.98
    f
    0.96
    Activations Density 0.000%

    No Known Activations