© 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. 113562
    Prev
    Next
    INDEX
    Explanations

    its followed by a noun

    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
    ри
    1.45
    ер
    1.40
     was
    1.30
    리
    1.17
    ็ต
    1.13
    ва
    1.07
     oxid
    1.05
    رة
    1.05
    ة
    1.03
    я
    1.02
    POSITIVE LOGITS
    it
    1.63
     a
    1.33
     it
    1.20
    ק
    1.13
    ش
    1.03
    which
    1.01
    avimo
    0.99
    ма
    0.98
    ்க்
    0.94
    ،
    0.93
    Activations Density 0.003%

    No Known Activations