© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36266
    Prev
    Next
    INDEX
    Explanations

    package manager

    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_3_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
    Packet
    0.68
    RY
    0.63
     从
    0.63
    Č
    0.63
    BIT
    0.62
    Š
    0.62
    PACK
    0.62
    '");
    0.62
    -
    0.62
    EX
    0.59
    POSITIVE LOGITS
    و
    0.64
    ι
    0.62
    ד
    0.60
    ни
    0.59
    ्य
    0.59
     չ
    0.55
    터
    0.54
    ну
    0.53
    кого
    0.52
    ким
    0.52
    Activations Density 0.009%

    No Known Activations