© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3991
    Prev
    Next
    INDEX
    Explanations

    code comments and import statements

    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_39_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
    لاص
    0.44
     버튼
    0.37
    łach
    0.37
     Warburton
    0.37
     vermiş
    0.36
    clen
    0.36
     ജോ
    0.35
    뉸
    0.35
    뎁
    0.35
    DataProvider
    0.35
    POSITIVE LOGITS
     Heimat
    0.37
    fst
    0.37
    ยนตร์
    0.34
     Multiply
    0.33
    Multiply
    0.33
     Edelstahl
    0.33
     rust
    0.33
    τ
    0.33
     PN
    0.33
     Bond
    0.32
    Activations Density 0.000%

    No Known Activations