© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165372
    Prev
    Next
    INDEX
    Explanations

    pleas, ples, please

    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_13_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
    🤎
    0.56
    㵴
    0.52
    деги
    0.52
     ž
    0.51
    ಾಗಿ
    0.51
     laranja
    0.51
     Thankfully
    0.50
     Santé
    0.50
     Parmi
    0.50
     کوډ
    0.50
    POSITIVE LOGITS
    schen
    0.57
    You
    0.56
    ע
    0.54
    우
    0.54
    س
    0.52
    ましょう
    0.52
    TS
    0.51
    Take
    0.51
    梁
    0.51
    uresh
    0.50
    Activations Density 0.000%

    No Known Activations