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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 196812
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_26_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
     is
    0.44
     serves
    0.40
     Music
    0.40
     Кстати
    0.39
     isn
    0.38
    ګ
    0.38
     Braves
    0.38
     Public
    0.37
     هی
    0.37
     Glass
    0.37
    POSITIVE LOGITS
    ологі
    0.48
    步
    0.47
     ouders
    0.46
    ิตร
    0.45
    							
    0.44
    退
    0.43
     jobb
    0.42
    獨立
    0.42
    多少
    0.42
    步驟
    0.42
    Activations Density 0.000%

    No Known Activations