© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9571
    Prev
    Next
    INDEX
    Explanations

    code and numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    hem
    0.75
     Spin
    0.71
     ：
    0.69
     중간
    0.68
     اک
    0.68
     Sponge
    0.68
     يم
    0.68
     상
    0.67
    ɺ
    0.66
     테이블
    0.64
    POSITIVE LOGITS
     heres
    0.74
    Dans
    0.72
     આવ્યું
    0.70
    Here
    0.69
    Its
    0.68
    astikan
    0.67
     Agus
    0.67
    réd
    0.67
     compat
    0.66
    BES
    0.64
    Activations Density 0.011%

    No Known Activations