© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6299
    Prev
    Next
    INDEX
    Explanations

    completed actions

    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_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
    ories
    1.16
     Воз
    1.14
    a
    1.06
    более
    1.03
     Поскольку
    1.00
    𝑎
    1.00
     Некоторые
    0.98
    🏼
    0.97
     sucesivamente
    0.95
    спользу
    0.95
    POSITIVE LOGITS
    ে
    1.07
    卓
    0.99
    ক
    0.99
    wasser
    0.98
    ech
    0.98
    heastern
    0.98
    nicy
    0.95
     galima
    0.95
    ká
    0.94
    niv
    0.92
    Activations Density 0.026%

    No Known Activations