© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82094
    Prev
    Next
    INDEX
    Explanations

    address

    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
     in
    1.45
    ти
    1.23
    ين
    1.20
    الي
    1.19
    f
    1.17
    {
    1.10
     في
    1.09
    c
    1.04
    та
    1.03
    )
    1.03
    POSITIVE LOGITS
    न
    1.81
    ای
    1.58
    ী
    1.56
    ン
    1.56
    한
    1.55
    3
    1.55
    یت
    1.52
    지
    1.52
    2
    1.45
    어
    1.45
    Activations Density 0.000%

    No Known Activations