© 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. 138839
    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
    MIR
    0.38
     SUPPL
    0.38
     Sommer
    0.37
     domain
    0.37
    umination
    0.36
    UY
    0.36
     spatially
    0.35
    殴
    0.35
    Spatial
    0.35
    teur
    0.35
    POSITIVE LOGITS
     탱크
    0.40
     wordArray
    0.39
    ジタル
    0.39
    回头
    0.38
     endGame
    0.38
    HasFieldError
    0.38
    sdk
    0.38
     startActivity
    0.37
    禄
    0.37
     perdere
    0.37
    Activations Density 0.000%

    No Known Activations