© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3319
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    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_5_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
     esteja
    1.75
    ख
    1.74
    து
    1.68
    要想
    1.57
    ל
    1.56
     समर्थक
    1.53
    मेंट
    1.51
    CH
    1.48
    kbar
    1.47
    राम
    1.46
    POSITIVE LOGITS
    smt
    1.78
    FFFFFF
    1.67
    ્સ
    1.65
     gtk
    1.64
     FNA
    1.64
    jing
    1.64
     polystyrene
    1.60
    ы
    1.57
    ្ល
    1.57
    ói
    1.55
    Activations Density 0.000%

    No Known Activations