© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205656
    Prev
    Next
    INDEX
    Explanations

    New York strings

    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_37_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
     Ελλάδα
    0.39
     prophylactic
    0.37
    ீன்
    0.37
    ቦ
    0.37
     Mussolini
    0.36
    mtq
    0.36
     location
    0.36
     autocl
    0.36
     chav
    0.36
    isés
    0.35
    POSITIVE LOGITS
    
    0.40
    stack
    0.38
     Consumers
    0.38
     stacks
    0.38
    apus
    0.38
    ocene
    0.37
    apur
    0.36
     Верхов
    0.36
    前端
    0.36
    itre
    0.36
    Activations Density 0.006%

    No Known Activations