© 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. 198388
    Prev
    Next
    INDEX
    Explanations

    bounce and grapefruit

    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
    იმ
    0.55
    ４
    0.54
     reloading
    0.50
     speculating
    0.50
    隈
    0.49
    䀦
    0.48
    ი
    0.48
     eyelids
    0.47
    🄰
    0.47
    cipe
    0.47
    POSITIVE LOGITS
    better
    0.59
     V
    0.57
    CO
    0.55
     Teachers
    0.55
     KEY
    0.54
     BETTER
    0.54
    PO
    0.53
    res
    0.52
     Causes
    0.52
     K
    0.52
    Activations Density 0.000%

    No Known Activations