© 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. 62877
    Prev
    Next
    INDEX
    Explanations

    stirring constantly

    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
     ujung
    0.40
     kib
    0.39
    bamos
    0.39
     ভাইস
    0.38
     penyeleng
    0.38
    誘導
    0.37
    㚐
    0.36
    ্যাশ
    0.35
     Ivy
    0.35
    beach
    0.34
    POSITIVE LOGITS
     stir
    2.44
     stirring
    2.36
     Stir
    2.34
    stir
    2.22
     stirred
    2.20
     stirs
    2.20
     stirrer
    1.94
    搅拌
    1.91
    攪
    1.61
    搅
    1.38
    Activations Density 0.006%

    No Known Activations