© 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. 7270
    Prev
    Next
    INDEX
    Explanations

    British Columbia and Canada

    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
    ()=>{
    2.96
    ೇ
    2.69
     pretty
    2.61
    pretty
    2.58
    值
    2.53
    पणे
    2.52
    ⺌
    2.52
    ूत
    2.48
    throws
    2.47
     berapa
    2.47
    POSITIVE LOGITS
    ل
    3.87
    ल
    3.47
    ब
    2.99
    ма
    2.94
    ᴅ
    2.94
     tudi
    2.93
    ᴘ
    2.90
    ই
    2.90
     étages
    2.84
    وجه
    2.83
    Activations Density 0.005%

    No Known Activations