© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105555
    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_1_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
    0
    1.60
    of
    1.38
     of
    1.33
    ي
    1.27
     are
    1.27
    ва
    1.27
     for
    1.21
     can
    1.21
    ０
    1.21
     at
    1.16
    POSITIVE LOGITS
    ני
    0.94
    ri
    0.94
    lings
    0.87
    ).
    0.86
    k
    0.85
    kannya
    0.85
    rade
    0.84
    ls
    0.84
    lanan
    0.83
    gruppen
    0.81
    Activations Density 0.000%

    No Known Activations