© 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. 213537
    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
    poi
    0.46
     poi
    0.43
    IAS
    0.41
    рою
    0.40
    엿
    0.39
     politico
    0.38
    дио
    0.36
    顏
    0.36
     dop
    0.35
     IA
    0.35
    POSITIVE LOGITS
     оку
    0.42
    Von
    0.41
    amatkan
    0.41
    OLS
    0.40
    lığı
    0.39
     uscita
    0.39
     Von
    0.38
    JAVADOC
    0.38
    ysa
    0.38
    egraphics
    0.37
    Activations Density 0.000%

    No Known Activations