© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 159360
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    (
    1.24
    ен
    1.23
    л
    1.10
    ல்
    1.09
    ೊ
    1.09
    ス
    1.08
    見た
    1.05
    的
    1.05
     pressur
    1.01
    ى
    0.98
    POSITIVE LOGITS
    u
    2.02
    p
    1.81
    i
    1.69
    y
    1.48
    is
    1.41
    m
    1.39
    you
    1.38
    n
    1.37
    o
    1.34
    x
    1.33
    Activations Density 0.000%

    No Known Activations