© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54519
    Prev
    Next
    INDEX
    Explanations

    research preview non-commercial use

    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_31_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
     oldest
    0.43
     తీ
    0.42
     टेंपरे
    0.40
     tempor
    0.38
    ㄐ
    0.38
     उम्र
    0.38
    យក
    0.38
     Tempor
    0.37
     temporal
    0.37
     Temporal
    0.37
    POSITIVE LOGITS
     پردا
    0.41
    CHANG
    0.37
     accurately
    0.36
     Gleason
    0.35
     chang
    0.35
    Gr
    0.35
     Grac
    0.34
     CHANG
    0.34
    創
    0.34
    Glo
    0.34
    Activations Density 0.004%

    No Known Activations