© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135465
    Prev
    Next
    INDEX
    Explanations

    present tense

    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_1_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
    ib
    1.22
    ﻓ
    1.14
    arı
    1.11
    ளும்
    1.11
    larında
    1.10
    la
    1.08
    ları
    1.08
    aría
    1.06
    入れて
    1.05
    daki
    1.03
    POSITIVE LOGITS
    ం
    1.10
    를
    1.09
    ן
    1.05
    ன்
    1.05
     Leipzig
    1.02
     Strasbourg
    1.02
    사
    1.02
    ס
    1.02
    ี
    1.02
     Seahawks
    0.99
    Activations Density 0.000%

    No Known Activations