© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249652
    Prev
    Next
    INDEX
    Explanations

    say "fa" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     fast
    4.25
    fast
    3.61
    Fast
    3.47
     Fast
    3.39
    快
    3.25
     फास्ट
    2.69
    FAST
    2.67
     FAST
    2.58
     快
    2.42
    快的
    2.08
    POSITIVE LOGITS
    ayson
    0.38
    ensed
    0.37
    wari
    0.36
    quisite
    0.35
    слары
    0.35
    atori
    0.35
    මක්
    0.34
    ้อม
    0.33
    atán
    0.33
    ầm
    0.33
    Activations Density 0.009%

    No Known Activations