© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202128
    Prev
    Next
    INDEX
    Explanations

    user input `prompt`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    APY
    0.43
    Enh
    0.39
    炇
    0.39
     Bulgarian
    0.38
     warp
    0.38
    Css
    0.38
    бки
    0.38
    ຖ
    0.38
    凹
    0.38
    ेंसी
    0.38
    POSITIVE LOGITS
    fangen
    0.37
     माध्य
    0.37
    ライン
    0.36
    ポン
    0.36
     histogram
    0.35
     veri
    0.35
     newborn
    0.34
     okay
    0.34
     stables
    0.34
    printk
    0.34
    Activations Density 0.001%

    No Known Activations