© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    trunk

    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
    s
    1.38
    ের
    0.92
    m
    0.84
    ال
    0.83
    র
    0.83
    idbody
    0.83
     povol
    0.83
    ,}
    0.81
    )},\
    0.79
     ferrovi
    0.79
    POSITIVE LOGITS
    beitet
    1.18
    يها
    1.12
    ত্যার
    1.04
    ことになる
    1.04
     gels
    1.04
    tei
    1.03
     comenz
    1.01
    hs
    1.00
    ষ্কৃত
    1.00
     lobbies
    0.99
    Activations Density 0.008%

    No Known Activations