© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162086
    Prev
    Next
    INDEX
    Explanations

    ils followed by verbs

    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
    ле
    1.34
    ست
    1.32
    нос
    1.22
    ко
    1.13
    ية
    1.08
    ރު
    1.06
    行う
    1.06
    ב
    1.04
    っている
    1.00
    tedir
    0.99
    POSITIVE LOGITS
    น
    1.39
     in
    1.11
    n
    1.03
     you
    1.02
    ar
    1.01
     tän
    0.99
    en
    0.95
    н
    0.94
    ن
    0.93
    ol
    0.90
    Activations Density 0.000%

    No Known Activations