© 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. 195265
    Prev
    Next
    INDEX
    Explanations

    behind your back

    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
     spare
    0.54
     তাঁর
    0.48
     downtime
    0.46
     scratching
    0.46
     scrot
    0.44
    衩
    0.43
     well
    0.43
    遮
    0.43
     commenced
    0.42
     spares
    0.42
    POSITIVE LOGITS
    พ
    0.64
    inan
    0.60
     ውሃ
    0.58
    n
    0.55
     ܗܘ
    0.54
    p
    0.53
    ub
    0.52
    irana
    0.52
     ምግብ
    0.52
    akkh
    0.50
    Activations Density 0.001%

    No Known Activations