© 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. 195259
    Prev
    Next
    INDEX
    Explanations

    zeros

    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
     性
    0.34
     changes
    0.33
    它可以
    0.33
    ieren
    0.32
    Changes
    0.32
     cambios
    0.32
     Changes
    0.32
     изменений
    0.31
    ल्पना
    0.31
     它
    0.31
    POSITIVE LOGITS
    ed
    0.44
     veliki
    0.35
    ست
    0.35
     እንዲሁም
    0.35
     సన్ని
    0.34
    ал
    0.34
     وزارة
    0.34
    title
    0.33
    IN
    0.32
    alı
    0.32
    Activations Density 0.001%

    No Known Activations