© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166780
    Prev
    Next
    INDEX
    Explanations

    supplement

    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
     wont
    0.45
     PhoneNumber
    0.36
     dont
    0.36
     cantilever
    0.36
    priced
    0.35
    pgsql
    0.35
     gitt
    0.35
    訊
    0.35
     rhs
    0.34
    launched
    0.34
    POSITIVE LOGITS
    Supp
    0.89
     Supp
    0.89
     supp
    0.86
    Sup
    0.80
     Sup
    0.79
     sup
    0.78
    supp
    0.75
    Suppl
    0.73
    SUP
    0.71
     suplement
    0.71
    Activations Density 0.000%

    No Known Activations