© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194026
    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_4_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
    s
    0.42
     Finest
    0.40
    ากร
    0.40
    ਲਾ
    0.40
    లువ
    0.40
    ਾਸ
    0.40
    崁
    0.39
     remnant
    0.38
    ิ
    0.38
     optima
    0.37
    POSITIVE LOGITS
    uştur
    0.56
    riy
    0.55
     yaptı
    0.53
    ğinin
    0.50
     temel
    0.49
     librarians
    0.49
     zašt
    0.48
    ıma
    0.48
    lilik
    0.48
    Match
    0.47
    Activations Density 0.000%

    No Known Activations