© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212723
    Prev
    Next
    INDEX
    Explanations

    cover art and images

    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_5_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
     as
    1.38
    ص
    1.36
    ف
    1.30
    ב
    1.30
    ب
    1.27
    ق
    1.20
    ט
    1.17
     सबसे
    1.09
    क
    1.09
     to
    1.07
    POSITIVE LOGITS
    elt
    1.18
    ت
    1.01
    iert
    0.99
    emed
    0.98
    ür
    0.96
    nements
    0.95
    ete
    0.93
    ır
    0.93
    ți
    0.92
    ́c
    0.92
    Activations Density 0.000%

    No Known Activations