© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80591
    Prev
    Next
    INDEX
    Explanations

    specific terms

    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_53_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
    dum
    0.45
    罰
    0.44
     Dum
    0.43
     dum
    0.42
     inter
    0.41
    Dum
    0.41
    idum
    0.40
     cert
    0.39
    etz
    0.37
    クト
    0.37
    POSITIVE LOGITS
    バリ
    0.41
     wise
    0.40
    瑢
    0.40
     Chesapeake
    0.40
    wise
    0.39
     বৈ
    0.39
    Fiscal
    0.39
     Hickey
    0.38
    FETCH
    0.38
     Wise
    0.38
    Activations Density 0.003%

    No Known Activations