© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144598
    Prev
    Next
    INDEX
    Explanations

    en token

    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_0_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
    리
    1.44
    ຂໍ້ມ
    1.37
    こと
    1.31
     particulier
    1.28
    1.24
    ني
    1.23
    RefItem
    1.21
    欱
    1.21
    CurrentUser
    1.19
    LabelTool
    1.17
    POSITIVE LOGITS
    ↵
    1.80
    า
    1.72
    '
    1.63
    ו
    1.55
    en
    1.51
     I
    1.51
    ิ
    1.45
    <0x80>
    1.45
    ти
    1.43
    ih
    1.41
    Activations Density 0.000%

    No Known Activations