© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142370
    Prev
    Next
    INDEX
    Explanations

    islands

    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_46_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
     Trudeau
    0.41
    Personensuche
    0.38
     افواج
    0.37
    泳
    0.37
     trio
    0.37
    ര
    0.37
     خدم
    0.36
    轳
    0.36
    鴳
    0.36
    НІ
    0.36
    POSITIVE LOGITS
     islands
    0.82
     Islands
    0.77
     island
    0.69
    Island
    0.67
    island
    0.64
     ISLAND
    0.64
     Island
    0.63
     islas
    0.62
     islets
    0.60
     pulau
    0.60
    Activations Density 0.002%

    No Known Activations