© 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. 36172
    Prev
    Next
    INDEX
    Explanations

    practicing entrepreneur, administrator, holder

    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
                  
    0.37
    ających
    0.36
     iceberg
    0.36
     swimming
    0.35
    heer
    0.34
              
    0.34
    🇭
    0.34
     husky
    0.34
    hao
    0.33
     berg
    0.33
    POSITIVE LOGITS
    postcard
    0.46
    Inode
    0.39
    剤
    0.39
     alguno
    0.38
     Algun
    0.38
     postcard
    0.38
     ][
    0.37
    escens
    0.37
    ផ្ល
    0.37
     }(
    0.37
    Activations Density 0.010%

    No Known Activations