© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165314
    Prev
    Next
    INDEX
    Explanations

    cryptographic algorithms

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comple
    0.42
     дис
    0.34
     Heav
    0.34
     '
    0.33
     Mach
    0.33
    國內
    0.33
     BM
    0.32
     Whe
    0.32
     Korean
    0.32
    bem
    0.31
    POSITIVE LOGITS
     beerCount
    0.37
     resultCode
    0.36
    IsEmpty
    0.35
     ненави
    0.35
    ոտ
    0.35
    パートナー
    0.34
    鳇
    0.34
    ಷ್ಠ
    0.34
     planilla
    0.34
     partenaires
    0.34
    Activations Density 0.000%

    No Known Activations