© 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. 60754
    Prev
    Next
    INDEX
    Explanations

    son, n, an, Mexican,razole

    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
    r
    1.88
    s
    1.45
    l
    1.40
    in
    1.37
    u
    1.33
    ی
    1.13
    There
    1.13
    y
    1.12
    If
    1.09
    I
    1.07
    POSITIVE LOGITS
     can
    1.55
    ет
    1.22
     crecer
    1.15
    ва
    1.09
    ні
    1.03
     وي
    1.03
     carelessly
    1.02
    را
    1.01
     acuerdos
    1.00
    يب
    0.98
    Activations Density 0.005%

    No Known Activations