© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5788
    Prev
    Next
    INDEX
    Explanations

    peppercorn

    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
    न
    0.72
    dmg
    0.67
    ни
    0.67
    ट
    0.66
     scant
    0.65
     sparing
    0.64
    ر
    0.64
    ра
    0.63
     kanan
    0.63
    𝐎
    0.61
    POSITIVE LOGITS
    ونم
    0.64
    ون
    0.64
    gono
    0.61
     الصحي
    0.60
     correr
    0.60
     devenu
    0.58
    Esse
    0.58
     vanes
    0.57
    kých
    0.57
    鳎
    0.56
    Activations Density 0.002%

    No Known Activations