© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167161
    Prev
    Next
    INDEX
    Explanations

    我

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    待
    0.41
     espero
    0.41
     concerned
    0.41
     Espero
    0.40
     câte
    0.40
     hoping
    0.39
     realise
    0.39
     희
    0.39
     esperanza
    0.39
     надеюсь
    0.38
    POSITIVE LOGITS
     नाहीत
    0.37
    別
    0.36
    还是要
    0.36
     encore
    0.35
    𝑙
    0.35
    گان
    0.35
    精
    0.35
    HEAP
    0.35
     نداشت
    0.34
    给大家
    0.34
    Activations Density 0.001%

    No Known Activations