© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178703
    Prev
    Next
    INDEX
    Explanations

    factorial recursion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
    HTree
    0.40
    舢
    0.39
    <0x94>
    0.38
     टमाटर
    0.37
     tabindex
    0.37
     सहानु
    0.37
    不再
    0.36
     abruptly
    0.36
    expandedTitle
    0.36
    輿
    0.36
    POSITIVE LOGITS
     schm
    0.40
    個人
    0.38
     kuris
    0.37
     ব্যক্তিগত
    0.36
    াদিত
    0.36
     Blizzard
    0.36
    нэт
    0.36
     citadel
    0.36
    攒
    0.36
     bestimmten
    0.36
    Activations Density 0.002%

    No Known Activations