© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59781
    Prev
    Next
    INDEX
    Explanations

    words like "tow" and "stow"

    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_2_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
     at
    1.03
    ll
    1.02
    ।
    1.00
    dır
    0.99
     in
    0.96
    ،
    0.96
     of
    0.96
    。
    0.93
    ，
    0.87
    ३
    0.86
    POSITIVE LOGITS
     возмо
    1.13
    ای
    1.08
    ו
    1.08
    h
    1.02
    un
    1.00
    ᅢ
    1.00
     nuovi
    0.99
    中断
    0.98
     νέα
    0.98
     い
    0.96
    Activations Density 0.015%

    No Known Activations