© 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. 58821
    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
    (
    1.64
    ли
    1.44
    (.*
    1.07
    も
    0.99
     ~(~)
    0.93
     ©️
    0.91
    ("--
    0.90
     ⿰
    0.89
     r
    0.88
    (\
    0.88
    POSITIVE LOGITS
    as
    2.14
    a
    2.00
    an
    1.86
    i
    1.84
    at
    1.83
    o
    1.73
    า
    1.70
    no
    1.38
    et
    1.36
    el
    1.34
    Activations Density 0.000%

    No Known Activations