© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79572
    Prev
    Next
    INDEX
    Explanations

    numbers and periods

    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
     ಮಧ್ಯ
    0.43
     خاص
    0.38
    ــــــــ
    0.38
    Რ
    0.38
     아주
    0.37
     hago
    0.36
     అతను
    0.36
     eks
    0.35
    dtypes
    0.35
     grille
    0.35
    POSITIVE LOGITS
    sf
    0.41
    íu
    0.39
    HOT
    0.36
    өнья
    0.36
    ativa
    0.35
    að
    0.35
     sf
    0.34
    ्यादा
    0.34
    ĭ
    0.34
     Sf
    0.34
    Activations Density 0.000%

    No Known Activations