© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201014
    Prev
    Next
    INDEX
    Explanations

    match and its applications

    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_6_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
    お客様
    0.98
    is
    0.92
    ต์
    0.89
    지
    0.88
    지에
    0.88
     yarns
    0.87
    வது
    0.85
     universidades
    0.84
    お客
    0.84
    ینگ
    0.83
    POSITIVE LOGITS
    Time
    1.04
    Sh
    0.90
    ്രീ
    0.87
    2
    0.87
    R
    0.84
    Insight
    0.83
    Sur
    0.82
    Session
    0.81
    ре
    0.80
    N
    0.80
    Activations Density 0.002%

    No Known Activations