© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34828
    Prev
    Next
    INDEX
    Explanations

    anagrams of words ending in "itory" or "way"

    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_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
    ay
    0.69
    ﺩ
    0.69
     i
    0.68
    érico
    0.66
     phospho
    0.64
     y
    0.63
     والم
    0.62
     hopeless
    0.61
     battleship
    0.60
    ﻉ
    0.60
    POSITIVE LOGITS
    ки
    1.02
    an
    0.93
    н
    0.82
    ان
    0.77
    נ
    0.77
    т
    0.75
    не
    0.71
    ра
    0.70
    ю
    0.68
    ้
    0.67
    Activations Density 0.007%

    No Known Activations