© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109153
    Prev
    Next
    INDEX
    Explanations

    "Ces" or "es" followed by nouns

    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
    ط
    1.38
    א
    1.16
    ка
    1.15
    ม
    1.08
    ки
    1.06
    та
    1.02
     débil
    1.01
    ි
    0.99
    ಯ
    0.97
    ੀ
    0.97
    POSITIVE LOGITS
    in
    2.00
    y
    1.77
    o
    1.77
    u
    1.56
    at
    1.51
    h
    1.44
    g
    1.38
    f
    1.38
    k
    1.30
    t
    1.25
    Activations Density 0.000%

    No Known Activations