© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181189
    Prev
    Next
    INDEX
    Explanations

    checking or verifying information

    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_24_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     individuale
    0.57
     calyce
    0.56
     ແ
    0.55
    elevationMap
    0.53
     বৃদ্ধি
    0.52
     attraverso
    0.52
    ఎస్‌
    0.52
     através
    0.52
     感じ
    0.51
     لیکن
    0.51
    POSITIVE LOGITS
     water
    0.53
    C
    0.51
    적
    0.46
    по
    0.44
    ch
    0.43
    water
    0.42
    در
    0.42
    水
    0.41
     Global
    0.40
     \
    0.40
    Activations Density 0.000%

    No Known Activations