© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200607
    Prev
    Next
    INDEX
    Explanations

    limited

    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_6_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
    ↵
    1.04
    ar
    0.99
     to
    0.94
    hala
    0.92
    INDI
    0.91
    h
    0.90
    ח
    0.90
    as
    0.88
    NERS
    0.82
    on
    0.81
    POSITIVE LOGITS
    ה
    1.13
    á
    1.08
    ı
    1.05
    ет
    1.01
    ;
    0.98
    ید
    0.93
    ε
    0.93
    ى
    0.92
    ில்
    0.91
    !=
    0.91
    Activations Density 0.002%

    No Known Activations