© 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. 163030
    Prev
    Next
    INDEX
    Explanations

    common occurrence

    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
    kal
    0.40
    大部分
    0.39
     ubiquitous
    0.35
     insecure
    0.34
    ('../../
    0.34
     Fuzzy
    0.34
    }.${
    0.34
    远
    0.34
     অধিকাংশ
    0.34
    kw
    0.34
    POSITIVE LOGITS
     monologue
    0.46
     ayuda
    0.42
    Maxima
    0.42
    ARIA
    0.41
     historia
    0.41
     मोटर्स
    0.40
     previa
    0.40
     Infants
    0.40
     infant
    0.39
    Chand
    0.39
    Activations Density 0.010%

    No Known Activations