© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1236
    Prev
    Next
    INDEX
    Explanations

    normalize image data

    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
    楪
    0.45
     tweezers
    0.43
    affen
    0.42
     Koenig
    0.42
    是非
    0.40
     এটাই
    0.40
     diaphragm
    0.39
     sympa
    0.39
    有り
    0.39
    靼
    0.39
    POSITIVE LOGITS
     Arter
    0.38
     thomas
    0.36
     তারিখে
    0.36
     decade
    0.35
    tub
    0.34
     tepung
    0.34
    Grain
    0.33
     एडिटिंग
    0.33
     род
    0.33
     Fourteenth
    0.33
    Activations Density 0.001%

    No Known Activations