© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    java Scanner input

    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
     seder
    1.48
    ূপ
    1.45
     manhã
    1.44
     twos
    1.42
    )}{\
    1.40
    ado
    1.40
    रों
    1.38
    ことなく
    1.37
     atro
    1.36
     hiçbir
    1.32
    POSITIVE LOGITS
    та
    1.61
    ღვ
    1.55
    𝙚
    1.41
     والمع
    1.39
     bract
    1.35
    лах
    1.35
    وترات
    1.35
    Uppercase
    1.31
     Elected
    1.30
     τὸν
    1.28
    Activations Density 0.001%

    No Known Activations