© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35179
    Prev
    Next
    INDEX
    Explanations

    Hawaiian culture

    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
     mele
    0.47
    ʄ
    0.40
    เล
    0.38
     bile
    0.38
     h
    0.37
     เพียง
    0.37
    óle
    0.37
    चय
    0.37
    له
    0.37
     दिग्
    0.37
    POSITIVE LOGITS
     nei
    0.59
    nei
    0.49
     Nei
    0.46
     k
    0.44
    pops
    0.43
     Holy
    0.42
    aho
    0.41
     Mus
    0.41
     grind
    0.41
    Holy
    0.41
    Activations Density 0.002%

    No Known Activations