© 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. 7811
    Prev
    Next
    INDEX
    Explanations

    winged victory, ascent, ess

    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
    ми
    2.86
    ி
    2.75
    ي
    2.73
     caseload
    2.59
    𝗻
    2.58
    ج
    2.53
    ه
    2.49
    য়া
    2.40
    بان
    2.40
    ప
    2.38
    POSITIVE LOGITS
    膀
    2.92
     noqa
    2.88
    offsetX
    2.62
    𝑵
    2.57
    ওলানা
    2.44
    ERSON
    2.44
    注意的是
    2.44
    cellaneous
    2.39
    边
    2.33
    ा
    2.30
    Activations Density 0.012%

    No Known Activations