© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105163
    Prev
    Next
    INDEX
    Explanations

    French words like bordure, bord, ban, or pro

    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_1_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
    ﺍ
    1.20
     divulg
    1.20
    로
    1.09
     delimit
    1.07
     diretor
    1.04
     imprimir
    1.04
     caract
    1.03
     posits
    1.02
     apenas
    1.01
     anglais
    0.99
    POSITIVE LOGITS
    一
    1.20
    ě
    1.13
    و
    1.10
    ↵↵
    1.02
    اً
    1.02
    j
    0.99
    ών
    0.96
    دين
    0.96
    است
    0.95
    л
    0.95
    Activations Density 0.001%

    No Known Activations