© 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. 213937
    Prev
    Next
    INDEX
    Explanations

    0

    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
     Specific
    0.39
    夶
    0.38
     Survey
    0.38
     खूप
    0.38
    荇
    0.38
    gpio
    0.37
     Union
    0.36
     Private
    0.35
    Peso
    0.35
    疋
    0.35
    POSITIVE LOGITS
     ({
    0.38
     octobre
    0.38
    aggers
    0.36
    ційних
    0.36
     atu
    0.34
     (;
    0.34
    minas
    0.34
     потеря
    0.34
    irer
    0.34
    ilmente
    0.34
    Activations Density 0.004%

    No Known Activations