© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54009
    Prev
    Next
    INDEX
    Explanations

    mongoose, Homo sapiens, connected databases

    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_30_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
    Γ
    0.32
     intric
    0.29
    Ê
    0.29
    ci
    0.28
    像素
    0.28
    +
    0.28
    '>
    0.28
     multit
    0.28
    ('/',
    0.27
     clipping
    0.26
    POSITIVE LOGITS
    ᓘ
    0.29
     regent
    0.28
    ßerdem
    0.27
     determinate
    0.27
    輋
    0.27
     सल्ला
    0.27
    arses
    0.27
     ValidationError
    0.26
     الحدود
    0.26
    룀
    0.26
    Activations Density 0.000%

    No Known Activations