© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205778
    Prev
    Next
    INDEX
    Explanations

    stairs or steps

    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_20_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
     olhos
    0.49
     tubuh
    0.43
    뀜
    0.42
     lichaam
    0.41
     spesies
    0.41
    Substring
    0.41
     khởi
    0.40
    种
    0.40
     선정
    0.40
     olho
    0.40
    POSITIVE LOGITS
     अंतरराष्ट्रीय
    0.47
     تدخل
    0.44
    istiche
    0.43
    istance
    0.43
    economic
    0.42
    疋
    0.42
     प्रश्
    0.41
    쟈
    0.41
    俨
    0.41
     सिखा
    0.40
    Activations Density 0.001%

    No Known Activations