© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245454
    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
     ei
    1.24
     crashes
    1.09
    ü
    1.03
     ease
    1.02
    の使用
    1.01
    or
    1.01
     ill
    0.99
    ś
    0.99
     ner
    0.98
     misused
    0.98
    POSITIVE LOGITS
    வியில்
    1.19
    бре
    1.17
     количеством
    1.16
    ያ
    1.15
     консульта
    1.13
     শক্তিশালী
    1.12
     cardiaque
    1.12
    న్న
    1.10
    ángulo
    1.10
     BusABC
    1.09
    Activations Density 0.000%

    No Known Activations