© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18280
    Prev
    Next
    INDEX
    Explanations

    expenses and assets

    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_15_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
    榱
    0.35
     اله
    0.34
    ası
    0.34
    閁
    0.33
    ang
    0.33
     lijst
    0.33
    मॉडल
    0.32
     modelli
    0.32
     గౌ
    0.32
     मकान
    0.31
    POSITIVE LOGITS
     month
    0.30
    ibouti
    0.29
     &/
    0.28
    ៊
    0.27
     теркәлү
    0.27
    processing
    0.27
    cards
    0.27
    mother
    0.27
    Occup
    0.27
     сутки
    0.27
    Activations Density 0.007%

    No Known Activations