© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41269
    Prev
    Next
    INDEX
    Explanations

    ETSI TS standards

    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_3_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
    s
    0.82
    ни
    0.82
    ের
    0.72
    ों
    0.64
    -
    0.64
    ओं
    0.63
     terug
    0.60
    ları
    0.59
    );\
    0.59
    ୍
    0.58
    POSITIVE LOGITS
    D
    0.80
    M
    0.76
    ر
    0.74
    ტის
    0.70
    맇
    0.64
    hā
    0.62
     it
    0.61
    ل
    0.61
    ਰ
    0.61
     Иң
    0.61
    Activations Density 0.002%

    No Known Activations