© 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. 133640
    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
    lada
    0.43
     Poets
    0.42
    ్లా
    0.41
    reetype
    0.38
    ominator
    0.38
     Owl
    0.37
     포
    0.36
     homozyg
    0.35
    owl
    0.35
     पो
    0.34
    POSITIVE LOGITS
     چکی
    0.47
     யு
    0.45
    oches
    0.44
     യുവ
    0.43
    丘
    0.43
     Chel
    0.41
     یونی
    0.39
     mortars
    0.39
     clearTimeout
    0.39
     चिकित्सकों
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.