© 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. 209544
    Prev
    Next
    INDEX
    Explanations

    bindings

    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
    Negative Logits
    '
    1.54
    i
    1.37
    >
    1.21
    \
    1.17
    s
    1.13
    0
    1.13
     was
    1.09
    ي
    1.09
    !
    1.07
    ;
    1.05
    POSITIVE LOGITS
    ान
    1.19
    ائی
    1.16
    ᱘
    1.12
    ﺄ
    1.10
    ん
    1.08
    ل
    1.06
    ар
    1.04
    on
    1.02
    м
    1.02
    ુ
    1.01
    Activations Density 0.000%

    No Known Activations