© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206363
    Prev
    Next
    INDEX
    Explanations

    grammatical parts of speech

    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_20_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
    }]}
    0.42
     এর
    0.41
     Хар
    0.40
    ખ્યા
    0.40
     까
    0.40
    bracht
    0.39
     الأخيرة
    0.39
     нев
    0.39
     Starting
    0.39
     something
    0.38
    POSITIVE LOGITS
    Якщо
    0.46
    інки
    0.45
    分布
    0.43
     vulgaris
    0.43
    dairy
    0.43
    杉
    0.43
    édez
    0.42
    tiene
    0.41
    iasis
    0.40
    Ꮕ
    0.40
    Activations Density 0.002%

    No Known Activations