© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175727
    Prev
    Next
    INDEX
    Explanations

    runtime error

    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_24_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
     ಕೈ
    0.40
     namani
    0.38
    拿
    0.37
     Deepika
    0.37
     vadanti
    0.37
     disfrut
    0.37
    ᅪ
    0.36
     zich
    0.36
     kend
    0.36
     побы
    0.36
    POSITIVE LOGITS
    
    0.41
    𐰴
    0.40
    罫
    0.39
     অসুস্থ
    0.39
     दुश्
    0.38
    ounce
    0.38
    uminescent
    0.37
    confusion
    0.37
     आतंक
    0.36
    Egg
    0.36
    Activations Density 0.000%

    No Known Activations