© 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. 133544
    Prev
    Next
    INDEX
    Explanations

    Entman framing

    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
     Blair
    0.47
     य
    0.46
     Klim
    0.42
     Y
    0.41
    szön
    0.40
     ی
    0.40
     حص
    0.40
     Klas
    0.39
     क्लाइ
    0.38
    ysters
    0.38
    POSITIVE LOGITS
    GIL
    0.42
    opolitical
    0.41
    লীর
    0.39
     Gilmore
    0.39
    hala
    0.38
    лке
    0.37
    manu
    0.37
    Carroll
    0.37
     दहेज
    0.37
    뎁
    0.36
    Activations Density 0.008%

    No Known Activations