© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231680
    Prev
    Next
    INDEX
    Explanations

    Hololive EN, Uma Musume, Arknights

    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_6_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
    *
    0.89
    umed
    0.84
    [
    0.83
    viä
    0.80
    cker
    0.78
    grams
    0.78
    A
    0.78
    ό
    0.78
    ]
    0.77
    ：
    0.77
    POSITIVE LOGITS
    t
    0.96
    en
    0.86
    ﺭ
    0.78
     radiological
    0.77
     pavimento
    0.76
    ar
    0.75
     percorso
    0.74
    رین
    0.73
     girls
    0.72
     referrer
    0.72
    Activations Density 0.000%

    No Known Activations