© 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. 19000
    Prev
    Next
    INDEX
    Explanations

    hills and landscapes

    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
    д
    0.48
     ස
    0.46
    ట్‌
    0.45
     HttpServlet
    0.45
    綎
    0.45
     !”
    0.44
    డ్‌
    0.44
    ட்
    0.44
    jars
    0.43
    л
    0.43
    POSITIVE LOGITS
     hill
    0.50
     hills
    0.50
     slope
    0.48
    Hill
    0.47
     Hill
    0.46
    Japanese
    0.44
    form
    0.42
    <
    0.42
    <em>
    0.41
    ISO
    0.41
    Activations Density 0.056%

    No Known Activations