© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7289
    Prev
    Next
    INDEX
    Explanations

    pseudo, sigmoidal, infections, sinus

    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
    2.71
     garam
    2.50
    й
    2.50
    ுங்கள்
    2.44
    ank
    2.32
    boden
    2.26
    ্স
    2.23
     그래도
    2.21
    Curs
    2.20
    Suy
    2.15
    POSITIVE LOGITS
    ➢
    3.07
    ্লিষ্ট
    2.80
    ➔
    2.76
    ться
    2.51
    ⎯
    2.48
    ฀
    2.48
    䀼
    2.41
    pseudo
    2.32
    ларга
    2.31
     foli
    2.30
    Activations Density 0.028%

    No Known Activations