© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46016
    Prev
    Next
    INDEX
    Explanations

    words following articles and possessives

    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_10_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
     invoc
    0.46
    ك
    0.42
     otáz
    0.42
     enfoc
    0.42
     azione
    0.42
    대
    0.41
     etapa
    0.41
     manglid
    0.41
    വസ
    0.41
     esclusivamente
    0.41
    POSITIVE LOGITS
    (
    0.50
    ą
    0.48
    ä
    0.46
    å
    0.46
    ;
    0.45
    7
    0.44
    9
    0.43
    á
    0.42
    ia
    0.42
    ik
    0.42
    Activations Density 0.099%

    No Known Activations