© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6062
    Prev
    Next
    INDEX
    Explanations

    DEFAULT CHARSET

    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_39_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
    尟
    0.38
     হয়েছিলেন
    0.35
    ENTION
    0.31
    िती
    0.31
    罟
    0.31
    욌
    0.31
     \}$
    0.30
     DeepCollection
    0.30
    "+"|".
    0.30
    }$=
    0.29
    POSITIVE LOGITS
     breath
    0.34
     pass
    0.30
    Therm
    0.30
     bas
    0.29
     best
    0.29
    Breath
    0.29
     कमजोरी
    0.28
     সম্র
    0.28
     Emperors
    0.28
     mask
    0.28
    Activations Density 0.001%

    No Known Activations