© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203415
    Prev
    Next
    INDEX
    Explanations

    ens and en prefixes

    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
    ر
    1.65
    ات
    1.57
    ו
    1.51
    و
    1.45
    ת
    1.44
    ت
    1.25
    트
    1.25
    o
    1.24
    ร
    1.23
    त
    1.18
    POSITIVE LOGITS
     was
    1.37
    </h2>
    1.27
     in
    1.20
     are
    1.20
    ari
    1.20
    ark
    1.17
    1
    1.17
     were
    1.13
     is
    1.09
    <0x0D>
    1.07
    Activations Density 0.001%

    No Known Activations