© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198729
    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_9_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
    Max
    0.51
    Mo
    0.46
    Yo
    0.46
    El
    0.45
    Talk
    0.43
    SA
    0.42
    高
    0.42
    MARK
    0.42
    Si
    0.41
    Soul
    0.41
    POSITIVE LOGITS
     senhores
    0.55
     comedian
    0.54
     italiani
    0.54
     insane
    0.53
     grava
    0.53
     jato
    0.50
     comical
    0.49
    existent
    0.49
     punctato
    0.49
    倰
    0.49
    Activations Density 0.000%

    No Known Activations