© 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. 8406
    Prev
    Next
    INDEX
    Explanations

    cryptography.hazmat

    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
    ucía
    0.73
    sière
    0.68
    udere
    0.68
    mouseDown
    0.67
    rück
    0.66
    дим
    0.65
    vrez
    0.65
    𝑎
    0.64
    drá
    0.64
    чё
    0.63
    POSITIVE LOGITS
    RE
    0.76
    আ
    0.75
    feather
    0.72
     Regularly
    0.72
    xtures
    0.70
     headings
    0.70
    စိတ်အပိုင်း
    0.69
    읊
    0.69
    ্যান্ড
    0.69
     Tại
    0.69
    Activations Density 0.001%

    No Known Activations