© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131118
    Prev
    Next
    INDEX
    Explanations

    pat

    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_50_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
     Eust
    0.44
     LISA
    0.43
     সিল
    0.42
    )^{(
    0.42
     AIS
    0.41
    LIS
    0.41
     Beech
    0.41
     কালি
    0.41
    Tonel
    0.40
    thorace
    0.40
    POSITIVE LOGITS
    PAT
    0.72
    pat
    0.71
     pat
    0.71
    Pat
    0.69
    apat
    0.68
     Pat
    0.65
    패
    0.63
     PAT
    0.61
     пат
    0.61
     Patriots
    0.57
    Activations Density 0.008%

    No Known Activations