© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111883
    Prev
    Next
    INDEX
    Explanations

    ler, Lee, Lean

    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_2_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
    t
    1.53
    n
    1.09
    c
    1.02
    l
    1.02
    en
    0.99
    る
    0.99
    ليه
    0.92
    ل
    0.92
    לך
    0.91
    inį
    0.90
    POSITIVE LOGITS
     in
    1.31
     to
    1.31
    It
    1.25
    In
    1.24
    س
    1.19
    й
    1.19
     It
    1.12
    та
    1.12
    م
    1.10
    ों
    1.09
    Activations Density 0.002%

    No Known Activations