© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174339
    Prev
    Next
    INDEX
    Explanations

    hair styles and states

    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
    ль
    0.38
    ่ม
    0.34
    ิบ
    0.34
     confession
    0.33
    ん
    0.33
    ഫ
    0.33
    льный
    0.33
    umbi
    0.33
    ви
    0.32
    чит
    0.32
    POSITIVE LOGITS
    ྞ
    0.39
    overrightarrow
    0.37
     পুনরা
    0.37
     Duo
    0.36
    写作
    0.36
    itaires
    0.35
     আক্রমণে
    0.35
     Gallagher
    0.35
     academically
    0.35
     Megan
    0.34
    Activations Density 0.003%

    No Known Activations