© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204800
    Prev
    Next
    INDEX
    Explanations

    burial and resting places

    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_25_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
     ලෙස
    0.33
     රස
    0.32
     ಬಿಜೆ
    0.27
     रुचि
    0.27
    齐
    0.26
     শাসনের
    0.26
     благо
    0.25
    高的
    0.25
    )_{
    0.25
    Fast
    0.25
    POSITIVE LOGITS
     funerals
    0.29
     differs
    0.27
     contains
    0.26
     IP
    0.25
     parade
    0.25
     midwife
    0.25
     preliminary
    0.25
    ства
    0.25
     widespread
    0.25
     preparations
    0.25
    Activations Density 0.002%

    No Known Activations