© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203831
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    affichage
    0.36
    ohon
    0.35
    ्रीम
    0.34
    >`;
    0.34
    श्विक
    0.33
    ovec
    0.33
    ove
    0.32
     більше
    0.32
    stva
    0.32
    ন্ত
    0.32
    POSITIVE LOGITS
    마
    1.23
    조
    1.12
     aj
    0.69
    ما
    0.64
    ма
    0.63
     má
    0.61
     Aj
    0.61
    调
    0.60
    Aj
    0.58
    má
    0.58
    Activations Density 0.001%

    No Known Activations