© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    css selectors

    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
    zęd
    1.68
     suoi
    1.68
     antiguos
    1.68
     Một
    1.66
    ecuzione
    1.61
     دارای
    1.58
    با
    1.57
    ع
    1.57
     Accueil
    1.56
     SUA
    1.56
    POSITIVE LOGITS
    empt
    1.30
     clapping
    1.29
    worst
    1.25
    reading
    1.25
    visible
    1.23
    fake
    1.21
    सन
    1.20
    quot
    1.16
    CPP
    1.13
    megaphone
    1.13
    Activations Density 0.032%

    No Known Activations