© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242101
    Prev
    Next
    INDEX
    Explanations

    at the [entity]

    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
     deceler
    0.38
    шинство
    0.36
    iasis
    0.35
    )|
    0.34
     ステン
    0.34
    %;
    0.34
     atrás
    0.34
     পুনঃ
    0.33
     snatch
    0.33
     আগেও
    0.33
    POSITIVE LOGITS
    αιν
    0.42
    प्या
    0.42
    Charting
    0.41
     Companion
    0.41
     richting
    0.40
     Commons
    0.39
    Requ
    0.39
    ピ
    0.38
     пути
    0.38
    forall
    0.38
    Activations Density 0.008%

    No Known Activations