© 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. 245584
    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
    т
    1.26
     Ό
    1.22
    ครอง
    1.21
     imposed
    1.14
     التي
    1.12
    鉗
    1.10
     differentiable
    1.08
     οποία
    1.08
    РЕ
    1.08
     которую
    1.08
    POSITIVE LOGITS
     Também
    1.09
    Hoje
    1.08
     também
    1.08
     fornece
    1.03
    apixel
    0.99
    맣
    0.98
     manej
    0.98
    aport
    0.97
    Suggest
    0.97
     verändert
    0.96
    Activations Density 0.000%

    No Known Activations