© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213699
    Prev
    Next
    INDEX
    Explanations

    harmful or illegal

    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_50_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
    влено
    0.39
    旨在
    0.38
     cubo
    0.38
    ствовать
    0.37
    alus
    0.37
    断
    0.37
    HARAD
    0.36
    GEM
    0.36
    الات
    0.35
    넛
    0.35
    POSITIVE LOGITS
     Dover
    0.41
    toNumber
    0.38
    ക്കാല
    0.38
    lin
    0.37
     دوره
    0.37
     Investigation
    0.36
    ものの
    0.36
     விரும்ப
    0.36
    toString
    0.36
    carriage
    0.36
    Activations Density 0.006%

    No Known Activations