© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38997
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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_57_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
    杍
    0.36
    잍
    0.36
     Ба
    0.35
    Btn
    0.35
     Ли
    0.35
     라이
    0.35
    체의
    0.35
     Пі
    0.35
    㕝
    0.35
    Sholes
    0.34
    POSITIVE LOGITS
     ​​
    0.42
      
    0.42
     ‎
    0.37
     autobi
    0.36
     ​​​​
    0.35
    0.35
    (?)
    0.35
     yearly
    0.34
     complicates
    0.34
    <0xE3>
    0.34
    Activations Density 0.040%

    No Known Activations