© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58398
    Prev
    Next
    INDEX
    Explanations

    Indian language initial syllables

    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    1.65
    ’
    1.35
     with
    1.33
     to
    1.31
     on
    1.18
     که
    1.13
    د
    1.10
    .’
    0.96
    ances
    0.95
     می‌
    0.94
    POSITIVE LOGITS
    м
    1.15
    녠
    1.03
    <0x80>
    0.96
    n
    0.96
     Cria
    0.96
    щение
    0.93
     Irlanda
    0.92
     publi
    0.91
     Anbieter
    0.87
    niveau
    0.87
    Activations Density 0.004%

    No Known Activations