© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38403
    Prev
    Next
    INDEX
    Explanations

    mixed technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     Gew
    0.39
     оби
    0.37
     Kön
    0.36
    ̼
    0.36
     beggars
    0.35
    ⿻
    0.35
    ارب
    0.34
    ைகளைக்
    0.34
    смо
    0.33
    tur
    0.33
    POSITIVE LOGITS
    Mess
    0.40
    ຕໍ່
    0.40
     Idani
    0.39
    udad
    0.39
     Mess
    0.38
     Customs
    0.37
    lvmama
    0.36
    置いて
    0.35
     mesi
    0.35
    凋
    0.35
    Activations Density 0.007%

    No Known Activations