© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166117
    Prev
    Next
    INDEX
    Explanations

    i followed by symbols

    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_31_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
    ativement
    0.36
     sharp
    0.34
    㖪
    0.34
    ань
    0.34
     Reaper
    0.34
     сложно
    0.33
    用
    0.33
     pur
    0.33
     characteristic
    0.32
     simpl
    0.32
    POSITIVE LOGITS
     helpless
    0.39
     Sommers
    0.39
     Investing
    0.38
    êtres
    0.37
    盆
    0.37
    ْت
    0.37
     Novo
    0.37
    зили
    0.37
     invest
    0.36
     latter
    0.36
    Activations Density 0.001%

    No Known Activations