© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206974
    Prev
    Next
    INDEX
    Explanations

    fields and properties

    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
     معلم
    0.48
    reflectionMap
    0.47
    锲
    0.46
    buildSpec
    0.46
     வகு
    0.46
    碩
    0.46
    漅
    0.46
     учащихся
    0.45
     ஆசிரிய
    0.45
     خد
    0.45
    POSITIVE LOGITS
    Mais
    0.48
    هر
    0.48
    Il
    0.45
     meas
    0.45
    Def
    0.44
    Je
    0.44
    É
    0.44
    It
    0.43
    Any
    0.43
     =
    0.43
    Activations Density 0.001%

    No Known Activations