© 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. 62935
    Prev
    Next
    INDEX
    Explanations

    linux 'ls' command

    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
    Negative Logits
    1.30
    I
    1.14
    o
    1.11
    y
    1.10
    In
    1.06
    ни
    1.05
    </h5>
    1.02
    ving
    1.02
    iding
    1.01
    />
    1.01
    POSITIVE LOGITS
    ש
    1.30
    يد
    1.27
     cinqui
    1.18
    lerine
    1.17
    ل
    1.16
     موسی
    1.15
     heps
    1.14
    lerinde
    1.13
     suivant
    1.12
    もう
    1.09
    Activations Density 0.000%

    No Known Activations