© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5937
    Prev
    Next
    INDEX
    Explanations

    application controllers and models

    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
    ل
    1.90
    ל
    1.82
    ્રોલ
    1.75
    тувати
    1.74
    म
    1.73
    ту
    1.67
    ب
    1.67
    م
    1.66
    ர
    1.65
    ベージュ
    1.63
    POSITIVE LOGITS
     kunna
    2.20
     পক্ষে
    2.02
    eenth
    1.95
    keyValue
    1.90
    tiba
    1.83
    valence
    1.83
    क्स्ट
    1.76
    originalname
    1.74
    breakers
    1.74
    𝙘
    1.72
    Activations Density 0.001%

    No Known Activations