© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198826
    Prev
    Next
    INDEX
    Explanations

    to be

    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_46_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
     low
    0.53
    低
    0.50
     easily
    0.49
     easier
    0.49
    Low
    0.47
     extremely
    0.44
     completamente
    0.44
     Low
    0.43
    low
    0.43
     completely
    0.43
    POSITIVE LOGITS
    来自于
    0.37
     مصدر
    0.36
    =<
    0.34
    出租
    0.34
    Member
    0.34
    স্ক
    0.34
    弟弟
    0.34
    凧
    0.34
    limiting
    0.33
     Wound
    0.33
    Activations Density 0.007%

    No Known Activations