© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156636
    Prev
    Next
    INDEX
    Explanations

    Sum

    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_50_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
    MAD
    0.41
    丙
    0.41
    JAM
    0.40
     lang
    0.40
    uku
    0.40
     Syntax
    0.39
     petal
    0.39
    uco
    0.38
    jak
    0.37
    ucha
    0.37
    POSITIVE LOGITS
    Generation
    0.42
    峄
    0.41
    [:-
    0.39
    вить
    0.39
     उर्वर
    0.39
    lire
    0.38
    ईआरटी
    0.37
    setObjectName
    0.37
    世代
    0.37
    consulté
    0.37
    Activations Density 0.000%

    No Known Activations