© 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. 14946
    Prev
    Next
    INDEX
    Explanations

    from

    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
    9
    0.63
    6
    0.63
    ets
    0.61
    8
    0.59
    7
    0.55
    0
    0.54
    5
    0.54
    av
    0.52
    ction
    0.50
    m
    0.50
    POSITIVE LOGITS
    嘴角
    0.60
     szy
    0.57
     ellipt
    0.56
     oczy
    0.56
     rarest
    0.56
     發
    0.56
    يمة
    0.56
     своїх
    0.56
     rosto
    0.55
     messageShow
    0.55
    Activations Density 0.001%

    No Known Activations