© 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. 20364
    Prev
    Next
    INDEX
    Explanations

    generating 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
    gen
    0.38
    𒐪
    0.38
    ゲン
    0.36
    ἁ
    0.35
    plaats
    0.34
    ისა
    0.34
     መጠ
    0.34
    ))){
    0.33
    ,+
    0.33
    θε
    0.33
    POSITIVE LOGITS
     tf
    0.66
     dns
    0.57
     aws
    0.56
     turkish
    0.54
     key
    0.53
     youtube
    0.51
     rss
    0.51
     intent
    0.51
     wordpress
    0.51
     llvm
    0.51
    Activations Density 0.058%

    No Known Activations