© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200316
    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_50_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
    TRE
    0.45
    Tre
    0.44
    asty
    0.44
    ぱ
    0.43
     Tre
    0.43
    tre
    0.43
     tre
    0.42
    тре
    0.42
     TRE
    0.42
     Draw
    0.41
    POSITIVE LOGITS
     Banff
    0.45
     Gallows
    0.40
    ՜
    0.39
     canoes
    0.38
     #+#
    0.38
    醍
    0.38
    ದ್ಯ
    0.37
     wading
    0.37
     Tenggara
    0.37
    wej
    0.37
    Activations Density 0.000%

    No Known Activations