© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252145
    Prev
    Next
    INDEX
    Explanations

    "nga", "bee", "dee"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    FieldName
    0.39
    an
    0.37
    Gut
    0.37
    취
    0.37
    Issledovatel
    0.36
     Fielding
    0.36
     cream
    0.35
    Sean
    0.35
    cannon
    0.35
    etric
    0.34
    POSITIVE LOGITS
    nga
    0.44
     bee
    0.42
     Bee
    0.41
     dee
    0.39
    ulele
    0.38
    نائ
    0.38
    नियर
    0.38
     디
    0.38
    nes
    0.38
    nesse
    0.38
    Activations Density 0.000%

    No Known Activations