Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165856
    Prev
    Next
    INDEX
    Explanations

    pop music

    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
     yıl
    0.58
     R
    0.56
     EDUC
    0.55
     Diels
    0.55
     chalc
    0.54
     guitarra
    0.54
     Guitar
    0.53
    quila
    0.53
    𝓷
    0.53
     Salary
    0.51
    POSITIVE LOGITS
    רה
    0.55
    डे
    0.49
    ুলে
    0.49
    ტიკ
    0.48
    ატი
    0.48
    unden
    0.47
    後に
    0.46
     choreographer
    0.46
    DeleteItem
    0.46
     الأولى
    0.46
    Activations Density 0.001%

    No Known Activations