© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157716
    Prev
    Next
    INDEX
    Explanations

    referring to

    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_2_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
    gers
    1.08
    ELL
    1.05
    nesses
    1.04
    ively
    0.90
     overboard
    0.87
     فراہم
    0.84
    EVEN
    0.84
    0.83
    s
    0.82
     assassin
    0.81
    POSITIVE LOGITS
    يل
    1.89
    ב
    1.85
    м
    1.80
    ى
    1.71
    ك
    1.66
    ب
    1.63
    وم
    1.61
    ي
    1.61
    م
    1.59
    ات
    1.56
    Activations Density 0.002%

    No Known Activations