© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103843
    Prev
    Next
    INDEX
    Explanations

    pod

    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_1_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
    ন
    1.64
    т
    1.38
    ר
    1.38
    ر
    1.38
    त
    1.34
    ン
    1.33
     as
    1.29
    ة
    1.25
    تي
    1.22
    น
    1.22
    POSITIVE LOGITS
    gan
    1.02
    burg
    0.93
    se
    0.91
    pathy
    0.91
    han
    0.91
    bli
    0.91
    ry
    0.90
    kee
    0.90
    oc
    0.88
    ید
    0.88
    Activations Density 0.002%

    No Known Activations