© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62813
    Prev
    Next
    INDEX
    Explanations

    parallel components

    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_41_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
    령
    0.47
    energie
    0.44
    energy
    0.43
    エネルギー
    0.43
    Energie
    0.42
     lymphocytic
    0.41
     एनर्जी
    0.40
    Energy
    0.38
    鐸
    0.38
     энергии
    0.38
    POSITIVE LOGITS
     Sixteen
    0.51
    南北
    0.50
     اینڈ
    0.43
     Return
    0.43
     gs
    0.38
     Мор
    0.38
     অ্যান্ড
    0.38
    Return
    0.37
    Six
    0.37
     北
    0.37
    Activations Density 0.001%

    No Known Activations