© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135247
    Prev
    Next
    INDEX
    Explanations

    vital signs and functions

    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_6_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
    .
    1.56
    س
    1.34
    ס
    1.33
    $
    1.20
    '
    1.16
    ’
    1.10
    اد
    1.05
    с
    1.05
    ز
    1.02
    .'
    1.02
    POSITIVE LOGITS
    an
    1.26
    la
    1.15
    he
    1.06
     Affordable
    1.04
    lt
    0.98
    </h3>
    0.98
    𖥔
    0.96
    larını
    0.96
     Shakti
    0.96
     Το
    0.96
    Activations Density 0.002%

    No Known Activations