© 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. 4853
    Prev
    Next
    INDEX
    Explanations

    screen, curses, stdscr

    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
    രുന്നു
    2.34
    ar
    2.29
    etable
    2.26
    standing
    2.13
    🅴
    2.13
    LAG
    2.10
    কার
    2.09
    ោង
    2.00
    Đây
    2.00
     fruition
    2.00
    POSITIVE LOGITS
    みると
    2.54
    pdb
    2.53
     Saltar
    2.50
    𝜇
    2.49
    𝑦
    2.43
     hạng
    2.43
    ល់
    2.42
     tels
    2.39
    該当
    2.37
    IVED
    2.34
    Activations Density 0.000%

    No Known Activations