© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14627
    Prev
    Next
    INDEX
    Explanations

    include Ruby code

    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_40_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
     self
    0.58
    self
    0.47
     த
    0.42
     selbst
    0.41
     自
    0.40
     zelf
    0.40
     selves
    0.40
     interfaces
    0.40
    陼
    0.40
    自
    0.39
    POSITIVE LOGITS
    INCLUDE
    0.63
    Include
    0.54
     Include
    0.49
     inclusion
    0.48
     IncludeField
    0.47
    Included
    0.46
     included
    0.46
     incluir
    0.46
    clusion
    0.45
     Inclusion
    0.45
    Activations Density 0.000%

    No Known Activations