© 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. 7991
    Prev
    Next
    INDEX
    Explanations

    heavily

    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
    ल
    0.90
     днем
    0.82
     trwa
    0.81
    LE
    0.77
    л
    0.74
     вот
    0.74
     społec
    0.74
    millimeters
    0.74
     bits
    0.74
     adanya
    0.73
    POSITIVE LOGITS
    지난
    0.76
    <0x80>
    0.71
     tbsp
    0.71
    ج
    0.70
    ত্ব
    0.70
    بت
    0.69
    е
    0.69
     laden
    0.68
    ασία
    0.66
    犸
    0.65
    Activations Density 0.010%

    No Known Activations