© 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. 8131
    Prev
    Next
    INDEX
    Explanations

    mental illness

    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
    s
    1.98
    bbene
    1.76
    <0x80>
    1.70
    srv
    1.57
    ע
    1.50
    lenen
    1.49
    sprintf
    1.49
    ()=>{
    1.48
    percent
    1.46
    €™
    1.45
    POSITIVE LOGITS
    ی
    2.97
    й
    2.33
    i
    2.10
    йся
    1.93
    ी
    1.86
    ి
    1.84
    ल
    1.76
    ი
    1.75
    یب
    1.69
    െ
    1.66
    Activations Density 0.001%

    No Known Activations