© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 137056
    Prev
    Next
    INDEX
    Explanations

    What followed by a word

    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_37_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
    想起
    0.40
    URNIZ
    0.38
     আসা
    0.37
     얻
    0.35
     дело
    0.35
    notepad
    0.35
     होत
    0.34
    agli
    0.34
    얻
    0.33
    菡
    0.33
    POSITIVE LOGITS
    what
    0.52
     what
    0.50
     therefore
    0.45
    therefore
    0.42
     ?"
    0.42
    ?»
    0.40
    Therefore
    0.40
    $?
    0.40
    सीएस
    0.39
     šta
    0.39
    Activations Density 0.000%

    No Known Activations