© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10053
    Prev
    Next
    INDEX
    Explanations

    pom.xml build.gradle project configuration SDK

    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_13_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
     Nói
    0.44
     Trouvez
    0.43
    州
    0.42
     නි
    0.41
     Сле
    0.40
    suz
    0.40
     Kết
    0.40
     Tanık
    0.40
     Trouver
    0.39
    Chaer
    0.39
    POSITIVE LOGITS
     process
    0.37
     iterate
    0.37
     if
    0.37
     pigment
    0.37
     subtracted
    0.37
     f
    0.36
    s
    0.36
     iteration
    0.36
     synthetic
    0.35
     liquid
    0.35
    Activations Density 0.065%

    No Known Activations