© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53609
    Prev
    Next
    INDEX
    Explanations

    Māori concepts

    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_55_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
     Aboriginal
    0.48
    Indigenous
    0.44
     Indigenous
    0.43
    暱
    0.39
    NSW
    0.38
    ונים
    0.38
    nodejs
    0.36
     вікісторінку
    0.36
     কুক
    0.35
     NSW
    0.35
    POSITIVE LOGITS
    Mara
    0.61
     mara
    0.60
     DH
    0.57
     Mara
    0.56
     i
    0.56
     Pas
    0.53
     ACC
    0.53
     Mau
    0.52
     mau
    0.50
     Treaty
    0.48
    Activations Density 0.000%

    No Known Activations