© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210255
    Prev
    Next
    INDEX
    Explanations

    Minoan civilization on Crete

    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_20_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
     Alaskan
    0.50
     ASS
    0.48
    ass
    0.46
     Alaska
    0.46
    ドン
    0.41
    idn
    0.40
    ASS
    0.39
    錆
    0.39
    却
    0.39
     ترین
    0.39
    POSITIVE LOGITS
     energia
    0.46
    სი
    0.46
     απαι
    0.45
    כה
    0.44
     debería
    0.44
    ǘ
    0.44
     должно
    0.44
     الملك
    0.43
     spese
    0.41
    स्कार
    0.41
    Activations Density 0.000%

    No Known Activations