© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42687
    Prev
    Next
    INDEX
    Explanations

    console.log statements

    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_22_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
    étr
    0.41
     Scala
    0.38
     Rif
    0.36
     suc
    0.35
    य
    0.35
     সৃষ্ট
    0.35
     Lis
    0.34
     Poké
    0.34
    마다
    0.34
    MPT
    0.34
    POSITIVE LOGITS
     antiquated
    0.43
     ધ્યા
    0.42
     entice
    0.42
     ል
    0.41
    YNAMICS
    0.40
    ኋላ
    0.40
    ร้อน
    0.40
    ้อมูล
    0.39
     بز
    0.39
     fusing
    0.39
    Activations Density 0.002%

    No Known Activations