© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211650
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
    Memorial
    0.42
     Memorial
    0.40
    平安
    0.39
    Miche
    0.36
    chakra
    0.36
    葡
    0.36
    షా
    0.36
     মাই
    0.36
    ┻
    0.36
    雛
    0.35
    POSITIVE LOGITS
     зае
    0.37
     ২৭
    0.36
     evidente
    0.36
    WOR
    0.36
    FAPI
    0.35
     invisible
    0.35
    관
    0.35
     robotics
    0.34
     กู
    0.34
     sık
    0.34
    Activations Density 0.001%

    No Known Activations