© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120117
    Prev
    Next
    INDEX
    Explanations

    asking for reason or cancellation

    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_27_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
     IAM
    0.30
    バリ
    0.30
     seven
    0.29
     Phenomen
    0.29
    ീ
    0.28
     complaints
    0.28
     chlorophyll
    0.28
     Clarion
    0.28
     America
    0.28
     Chicago
    0.28
    POSITIVE LOGITS
     coexist
    0.33
     жок
    0.29
     spust
    0.29
    独特的
    0.29
     innov
    0.28
    寯
    0.27
     зача
    0.27
    优先
    0.26
     পাহাড়
    0.26
    uiscono
    0.26
    Activations Density 0.001%

    No Known Activations