© 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. 33306
    Prev
    Next
    INDEX
    Explanations

    direct train to

    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
     टॉ
    0.39
    弓
    0.39
     घिरा
    0.39
     cozy
    0.37
     बे
    0.37
     côtes
    0.36
    肋
    0.35
     leads
    0.35
     ря
    0.34
     Fate
    0.34
    POSITIVE LOGITS
    digit
    0.36
     เขียน
    0.35
    蓥
    0.35
     unopened
    0.34
    룽
    0.34
    ┓
    0.34
    ʝ
    0.34
     ICM
    0.34
     pouv
    0.33
     unil
    0.33
    Activations Density 0.028%

    No Known Activations