© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33228
    Prev
    Next
    INDEX
    Explanations

    ton or tone

    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
    Negative Logits
    ли
    1.01
    ב
    0.85
    де
    0.84
    ᾖ
    0.79
    ING
    0.79
     toplant
    0.78
    र
    0.76
    И
    0.76
    р
    0.75
    ר
    0.75
    POSITIVE LOGITS
    ل
    0.75
    Ton
    0.71
    have
    0.70
     toneladas
    0.69
    Tone
    0.68
    ton
    0.65
    toned
    0.64
    Tonel
    0.63
     Ton
    0.62
     सामान
    0.61
    Activations Density 0.027%

    No Known Activations