© 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. 14835
    Prev
    Next
    INDEX
    Explanations

    **Observation steps**

    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
    elda
    0.52
    дера
    0.47
    Arabic
    0.47
    OL
    0.47
    OR
    0.46
    👪
    0.46
    ницей
    0.46
    ницы
    0.46
    New
    0.45
    Sap
    0.45
    POSITIVE LOGITS
     promptly
    0.50
     reportedly
    0.47
    тков
    0.47
    cesor
    0.47
     Obituary
    0.45
     РАН
    0.45
    甚至
    0.44
     n
    0.44
     যখন
    0.44
     ആദ്യം
    0.44
    Activations Density 0.021%

    No Known Activations