© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175708
    Prev
    Next
    INDEX
    Explanations

    typeof operator with type expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    ($
    0.47
    直
    0.42
    ด้าน
    0.41
    AR
    0.40
    unculus
    0.40
     Alger
    0.40
     Away
    0.39
     Cab
    0.38
     Desk
    0.38
    截
    0.38
    POSITIVE LOGITS
     졸업
    0.48
     hùng
    0.46
     practised
    0.46
     lí
    0.46
     próprio
    0.46
     reconoc
    0.45
     szerző
    0.45
     professores
    0.44
     methacrylate
    0.44
     koe
    0.44
    Activations Density 0.000%

    No Known Activations