© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205418
    Prev
    Next
    INDEX
    Explanations

    SwiftUI stacks

    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_6_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
    ized
    1.02
    0
    0.98
    ING
    0.91
    alk
    0.77
     näytt
    0.77
    4
    0.76
    類の
    0.75
    ắc
    0.75
     measuring
    0.75
    ER
    0.74
    POSITIVE LOGITS
    त
    1.48
    us
    1.45
    ва
    1.33
    ل
    1.23
    ת
    1.19
    т
    1.16
    that
    1.12
    ્સ
    1.11
    트
    1.11
    ור
    1.10
    Activations Density 0.001%

    No Known Activations