© 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. 4810
    Prev
    Next
    INDEX
    Explanations

    DeepMind

    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
     혁
    0.41
    嗳
    0.38
    अल
    0.38
    parad
    0.38
     гене
    0.37
    excell
    0.37
     क्रिस
    0.37
     Seafood
    0.36
     Freel
    0.36
     Landon
    0.36
    POSITIVE LOGITS
     뒤
    0.37
    rometry
    0.36
     चलेगी
    0.35
     retro
    0.35
    личи
    0.34
    нения
    0.34
    Bibliografia
    0.34
    뒤
    0.34
    izaje
    0.33
    rafos
    0.33
    Activations Density 0.018%

    No Known Activations