© 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. 6122
    Prev
    Next
    INDEX
    Explanations

    help me [verb]

    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
    岖
    2.25
     poč
    2.19
    xhr
    2.11
     पैमाने
    2.11
    وانه
    1.99
     suspected
    1.99
     appro
    1.98
    椎
    1.97
     endl
    1.96
    רים
    1.95
    POSITIVE LOGITS
     đỡ
    2.56
    ن
    2.36
    ми
    2.26
    то
    2.10
     tremendously
    2.03
    াল
    2.01
     ích
    2.00
    sht
    1.85
    닫
    1.85
     друзей
    1.84
    Activations Density 0.119%

    No Known Activations