© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59945
    Prev
    Next
    INDEX
    Explanations

    Burj Khalifa height and observation decks

    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_11_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
     instruct
    0.44
    ON
    0.41
    私
    0.39
     recover
    0.35
     describe
    0.34
     formally
    0.34
    泡
    0.34
     edit
    0.34
    О
    0.34
     consult
    0.33
    POSITIVE LOGITS
    äck
    0.42
     Lessor
    0.37
    ivore
    0.36
     ಡೇ
    0.35
    æng
    0.35
    encan
    0.35
    estellt
    0.34
    ä
    0.34
     ناو
    0.34
    emorrh
    0.33
    Activations Density 0.031%

    No Known Activations