© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116599
    Prev
    Next
    INDEX
    Explanations

    area in square miles or sq km

    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_27_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
     associated
    0.40
    </u>
    0.38
     constituency
    0.37
     Runners
    0.36
     understandably
    0.35
    หุ้น
    0.35
     Babies
    0.35
     throughout
    0.34
    ambra
    0.34
     ASSOCI
    0.34
    POSITIVE LOGITS
    કી
    0.51
     plabic
    0.40
    鐫
    0.38
    Contato
    0.38
    ैसे
    0.37
    Annual
    0.37
     वार्षिक
    0.37
     Elkus
    0.37
     قریب
    0.36
    酈
    0.36
    Activations Density 0.000%

    No Known Activations