© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 244499
    Prev
    Next
    INDEX
    Explanations

    id="

    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_40_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
    ധിപ
    0.43
    enemy
    0.39
    סק
    0.36
    otan
    0.35
     المال
    0.35
    쫄
    0.35
    ﹚
    0.35
    ชีพ
    0.34
    〟
    0.34
    lares
    0.34
    POSITIVE LOGITS
     indir
    0.39
    ACTION
    0.38
     loosen
    0.38
     Vás
    0.38
     ActionMode
    0.37
     اقدامات
    0.37
     LANGUAGES
    0.37
     القيمه
    0.37
     bắt
    0.36
    ActionButton
    0.36
    Activations Density 0.002%

    No Known Activations