© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7487
    Prev
    Next
    INDEX
    Explanations

    resources for more information

    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
    ده
    0.98
    ТА
    0.97
    is
    0.91
     destinés
    0.89
    𝑡
    0.89
     зато
    0.86
     mahal
    0.84
     taman
    0.84
    𝑖
    0.84
    ী
    0.84
    POSITIVE LOGITS
    殑
    0.78
    氵
    0.75
    addField
    0.73
    ựng
    0.72
     functor
    0.71
    eck
    0.71
    мене
    0.70
    敨
    0.68
    úč
    0.67
     trov
    0.67
    Activations Density 0.137%

    No Known Activations