© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130181
    Prev
    Next
    INDEX
    Explanations

    describing qualities or attributes

    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_25_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
    Variety
    0.39
     postul
    0.38
    講的是
    0.38
    simpleType
    0.36
     harms
    0.35
     മഹ
    0.35
    
    0.35
    āda
    0.35
     mekanisme
    0.35
     dahulu
    0.35
    POSITIVE LOGITS
    也就
    0.38
    驷
    0.35
     उसने
    0.34
    だったので
    0.34
     F
    0.33
     boys
    0.32
     تم
    0.32
     Arabs
    0.32
    巧
    0.32
     थे
    0.32
    Activations Density 0.001%

    No Known Activations