Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 245163
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_11_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
    ت
    1.61
    ки
    1.54
    er
    1.50
    cough
    1.46
     своим
    1.40
    hung
    1.40
    willing
    1.38
    ת
    1.33
    hills
    1.29
    tails
    1.28
    POSITIVE LOGITS
     Organización
    1.07
     asesinato
    1.03
    ४
    1.01
     Потом
    1.00
     resent
    1.00
     sé
    0.97
     trasport
    0.97
    ٹی
    0.96
    нии
    0.96
     하겠습니다
    0.94
    Activations Density 0.000%

    No Known Activations