© 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. 160308
    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
    iin
    1.27
    x
    1.07
    dı
    1.05
    am
    0.98
    corrected
    0.98
    েরা
    0.98
    iiv
    0.98
    i
    0.97
    can
    0.96
    tho
    0.96
    POSITIVE LOGITS
     as
    1.35
    ும்
    1.34
    س
    1.27
     of
    1.17
    ，
    1.17
    ме
    1.16
    ス
    1.15
    是
    1.13
    िंग
    1.10
     with
    1.09
    Activations Density 0.000%

    No Known Activations