© 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. 20733
    Prev
    Next
    INDEX
    Explanations

    R code

    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
     R
    1.89
    R
    1.51
     <-
    1.34
     الر
    1.18
    <-
    1.13
     shiny
    1.07
    Shiny
    1.07
     Shiny
    1.05
    shiny
    0.99
     Р
    0.97
    POSITIVE LOGITS
    →
    0.37
    ipheral
    0.37
    ppb
    0.36
    csp
    0.35
    
    0.35
    ＰＥＮＡＮＡ
    0.34
    ₄
    0.33
    罾
    0.33
    JQ
    0.32
    Feature
    0.32
    Activations Density 0.027%

    No Known Activations