© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3423
    Prev
    Next
    INDEX
    Explanations

    `to read`, `The input`, `The PIL`, `The first`, `The integer`, `The current`, `The radius`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    یسی
    0.97
     foremost
    0.94
    и
    0.89
    дагы
    0.88
    ﻧ
    0.85
    ρι
    0.84
     Особенно
    0.84
    inté
    0.82
    रा
    0.82
     Reprinted
    0.82
    POSITIVE LOGITS
     значение
    0.99
    zzo
    0.86
    se
    0.86
    人和
    0.84
     этой
    0.82
     squir
    0.82
     `#
    0.80
     متحده
    0.78
    ic
    0.78
     coals
    0.78
    Activations Density 0.162%

    No Known Activations