© 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. 63353
    Prev
    Next
    INDEX
    Explanations

    apparatus, trucks, sections

    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
     Enquiry
    0.43
     সহায়
    0.42
     সহায়তা
    0.40
     समर्
    0.39
     বিস্ফ
    0.39
    锥
    0.38
     Elbow
    0.38
    conven
    0.38
     Spit
    0.38
     مساعد
    0.38
    POSITIVE LOGITS
    appar
    0.46
     apparatus
    0.45
     apar
    0.43
     Apparatus
    0.43
     аппара
    0.41
     appar
    0.40
    ┈┈
    0.38
     Medium
    0.38
    ός
    0.37
     refractory
    0.37
    Activations Density 0.001%

    No Known Activations