© 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. 6112
    Prev
    Next
    INDEX
    Explanations

    python class __init__ self

    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
    GRO
    0.38
    वाडी
    0.38
     BELL
    0.35
    만
    0.35
     surfaces
    0.34
    engine
    0.33
     Pele
    0.33
    uole
    0.33
    BO
    0.32
    வோ
    0.32
    POSITIVE LOGITS
     föränd
    0.43
    ያው
    0.38
     Style
    0.36
     बदल
    0.36
     unifying
    0.35
    .([]
    0.35
     Strict
    0.35
     correcting
    0.35
    支給
    0.35
    ږئ
    0.34
    Activations Density 0.001%

    No Known Activations