© 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. 7319
    Prev
    Next
    INDEX
    Explanations

    dynamic content or behavior

    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
    м
    3.58
    paddle
    2.92
    অ্যাপ
    2.74
    
    2.74
    $).
    2.72
    additive
    2.62
    至於
    2.61
    tender
    2.60
     discontinuity
    2.59
    uance
    2.55
    POSITIVE LOGITS
    ки
    2.77
    وں
    2.65
     thuế
    2.46
    謐
    2.43
    谧
    2.39
    ą
    2.38
    𝐀
    2.35
    辄
    2.33
    あります
    2.33
    acinth
    2.32
    Activations Density 0.052%

    No Known Activations