© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135401
    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_37_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
    cmt
    0.40
    మంలో
    0.38
     جي
    0.38
     boasts
    0.37
    Jimmy
    0.36
    __.
    0.36
    cmml
    0.36
    KindOfClass
    0.35
    iced
    0.35
     Sponsored
    0.35
    POSITIVE LOGITS
    pyridazine
    0.42
    வா
    0.37
     duckys
    0.37
    ÓN
    0.37
     있게
    0.36
     veinte
    0.36
     लम्
    0.36
     сохрани
    0.36
    :-)
    0.35
     planis
    0.35
    Activations Density 0.000%

    No Known Activations