© 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. 249983
    Prev
    Next
    INDEX
    Explanations

    re

    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
     re
    0.70
    alternative
    0.47
    Alternative
    0.43
     alternative
    0.42
    downloads
    0.41
    再
    0.40
     Alternative
    0.40
     installs
    0.39
    visits
    0.39
    fails
    0.39
    POSITIVE LOGITS
    짜
    0.38
     Caring
    0.38
     হুগলীর
    0.37
    hnen
    0.37
     graze
    0.37
    번호
    0.37
    贿
    0.36
    이다
    0.36
     stare
    0.35
     Yar
    0.35
    Activations Density 0.002%

    No Known Activations