© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162505
    Prev
    Next
    INDEX
    Explanations

    phenomenon

    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_2_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
    ని
    1.20
    ме
    1.07
    -
    1.01
    $)$.
    1.00
    |
    1.00
    ми
    0.99
    కు
    0.98
    $
    0.96
    사
    0.96
    L
    0.95
    POSITIVE LOGITS
     for
    1.42
    p
    1.41
    for
    1.26
    ן
    1.19
     For
    1.13
    pV
    1.05
     the
    1.03
    ar
    1.02
     can
    1.02
     are
    0.96
    Activations Density 0.000%

    No Known Activations