© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81280
    Prev
    Next
    INDEX
    Explanations

    ¾ cup

    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_0_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
    。
    1.30
    genome
    1.19
    gere
    1.16
    gün
    1.13
    gruppe
    1.11
    gambar
    1.11
    går
    1.08
    data
    1.07
    vgl
    1.07
    gist
    1.06
    POSITIVE LOGITS
    ン
    1.98
    ش
    1.95
    ↵
    1.92
    리
    1.92
    я
    1.75
    ות
    1.71
    -
    1.69
    사
    1.68
    ला
    1.67
    り
    1.67
    Activations Density 0.001%

    No Known Activations