© 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. 204363
    Prev
    Next
    INDEX
    Explanations

    npm install

    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
    
    0.42
     $"{
    0.39
     Modern
    0.39
    ្យ
    0.37
     معلم
    0.37
    '%
    0.36
     mn
    0.35
    さえ
    0.35
    惫
    0.35
    frmt
    0.35
    POSITIVE LOGITS
     Chalmers
    0.37
     EDI
    0.36
    Favor
    0.36
    жал
    0.35
    行き
    0.34
    खार
    0.34
    EDI
    0.34
    arraf
    0.34
    قم
    0.33
     Ababa
    0.33
    Activations Density 0.001%

    No Known Activations