© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33434
    Prev
    Next
    INDEX
    Explanations

    warm place for rise

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ada
    0.37
     devils
    0.35
    ļa
    0.34
     FLAGS
    0.34
     Flags
    0.33
     zigzag
    0.33
    臘
    0.33
     Flores
    0.33
     bele
    0.33
     transvers
    0.33
    POSITIVE LOGITS
     لس
    0.35
     बचत
    0.35
    पंच
    0.34
    ɵ
    0.33
     رح
    0.32
    Thy
    0.31
    ትን
    0.31
     अवलोकन
    0.31
    ଠ
    0.31
    梦想
    0.30
    Activations Density 0.040%

    No Known Activations