© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3928
    Prev
    Next
    INDEX
    Explanations

    web links and javascript documentation

    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
     Display
    0.42
     métall
    0.40
     맨
    0.39
     suddenly
    0.39
     Renewable
    0.39
     Strawberry
    0.39
     Variant
    0.39
     Displays
    0.38
     Sacchar
    0.38
    观
    0.38
    POSITIVE LOGITS
    oclip
    0.38
     bruises
    0.36
     Rech
    0.36
    inding
    0.36
     rech
    0.35
     contradicting
    0.35
     consonants
    0.35
    kh
    0.35
     clipped
    0.34
     ಅನುಪ
    0.34
    Activations Density 0.000%

    No Known Activations