© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43734
    Prev
    Next
    INDEX
    Explanations

    code keywords and structure

    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_22_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
     multim
    0.46
    мости
    0.46
     kõige
    0.45
     Mili
    0.45
     absorbance
    0.44
     quench
    0.44
    阏
    0.43
    кинуло
    0.42
     bolster
    0.42
     activ
    0.42
    POSITIVE LOGITS
    THING
    0.40
    {
    0.40
     খোলা
    0.39
    [
    0.38
    ovy
    0.37
    女性
    0.37
    csv
    0.36
     كامل
    0.36
    Thing
    0.36
    oleic
    0.36
    Activations Density 0.000%

    No Known Activations