© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9028
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measurement

    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
    cloudinary
    0.40
    aisal
    0.38
    ᱖
    0.36
     Lum
    0.36
     anointed
    0.36
    ськ
    0.36
     इ
    0.35
    ೬
    0.35
    द्र
    0.35
     QApplication
    0.34
    POSITIVE LOGITS
     Lavinia
    0.38
    zoo
    0.38
    tdev
    0.38
    ReaderWriter
    0.37
    break
    0.36
    authier
    0.36
     ساک
    0.36
    subMenu
    0.35
    鳥
    0.35
     Birds
    0.35
    Activations Density 0.013%

    No Known Activations