© 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. 215762
    Prev
    Next
    INDEX
    Explanations

    imperfections make characters endearing

    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
     recreational
    0.41
     average
    0.36
     resulting
    0.35
     f
    0.35
    悗
    0.35
     Squid
    0.35
     worth
    0.34
     ফলে
    0.34
     กู
    0.34
     blows
    0.34
    POSITIVE LOGITS
    자를
    0.38
    rahmen
    0.37
    सह
    0.37
     ჩატი
    0.35
    )$\\
    0.35
    =>$
    0.35
    ින්
    0.34
    Inline
    0.34
     HB
    0.34
     identificado
    0.34
    Activations Density 0.005%

    No Known Activations