© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48514
    Prev
    Next
    INDEX
    Explanations

    image channels

    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_31_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
     bitterly
    0.35
    GISL
    0.33
     brushless
    0.30
     واح
    0.30
     です
    0.28
     elevationMap
    0.28
    MacroExpansion
    0.28
    綽
    0.28
    
    0.27
     แต
    0.27
    POSITIVE LOGITS
    Systems
    0.31
     mulighed
    0.31
    Human
    0.30
     možnosti
    0.30
     memulai
    0.30
     Human
    0.30
    }^{
    0.29
    类似于
    0.29
     alcool
    0.29
     rượu
    0.29
    Activations Density 0.002%

    No Known Activations