© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18756
    Prev
    Next
    INDEX
    Explanations

    Narrator or Host introductions

    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_15_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
    utional
    0.25
    忙
    0.25
     ক্ষত্র
    0.24
    能夠
    0.24
    Bigr
    0.24
    ड्यूल
    0.23
    RetValue
    0.23
     $>
    0.22
     použí
    0.22
    懂得
    0.22
    POSITIVE LOGITS
     κα
    0.27
    érées
    0.25
    ປະກ
    0.25
    ра
    0.24
    рай
    0.24
    лка
    0.24
     නො
    0.23
    тан
    0.23
     ка
    0.22
     violation
    0.22
    Activations Density 0.017%

    No Known Activations