© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6954
    Prev
    Next
    INDEX
    Explanations

    Edmund, Rand, Ralph

    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
     segi
    3.53
    orbits
    2.77
    ص
    2.75
     целей
    2.74
    𝜇
    2.72
    𝐻
    2.69
    中止
    2.67
    𝑔
    2.64
    ()=>{
    2.55
     AnyObject
    2.53
    POSITIVE LOGITS
    te
    3.09
    nie
    2.79
    ு
    2.57
    mé
    2.49
     través
    2.44
     ليست
    2.41
    se
    2.39
    ^{*
    2.38
    رات
    2.36
    sk
    2.34
    Activations Density 0.008%

    No Known Activations