© 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. 7754
    Prev
    Next
    INDEX
    Explanations

    overview

    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
    ことは
    1.97
    𝗧
    1.92
    ра
    1.90
    ு
    1.84
    𝗣
    1.83
    ্স
    1.75
    𝗗
    1.74
    ungsl
    1.72
    ४
    1.72
     fått
    1.71
    POSITIVE LOGITS
    ة
    2.18
    ع
    1.79
    ed
    1.77
    polyline
    1.76
     hectares
    1.71
     kuhusu
    1.69
     acreage
    1.65
    覧
    1.63
     unmatched
    1.63
    dotted
    1.63
    Activations Density 0.152%

    No Known Activations