© 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. 18971
    Prev
    Next
    INDEX
    Explanations

    toiletries

    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
    唠
    0.40
    for
    0.38
     clothed
    0.37
     Zinc
    0.36
    cares
    0.35
    长
    0.34
    nonlinear
    0.34
    basecode
    0.34
    or
    0.33
    નાં
    0.33
    POSITIVE LOGITS
     lại
    0.44
     prestation
    0.44
    贷款
    0.42
    ሃኒ
    0.41
     เด
    0.37
    ksyon
    0.36
    য়াল
    0.36
    き
    0.36
     employé
    0.35
    дын
    0.35
    Activations Density 0.012%

    No Known Activations