© 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. 243206
    Prev
    Next
    INDEX
    Explanations

    vercel

    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
    形态
    0.37
     morphology
    0.36
     Luka
    0.36
    ῶ
    0.36
     Issa
    0.35
     Nähe
    0.35
     morph
    0.35
    啼
    0.35
     শাখার
    0.34
    came
    0.34
    POSITIVE LOGITS
    }[(
    0.41
     Kobe
    0.39
    あまり
    0.38
     пля
    0.38
    ][%
    0.38
    ビーチ
    0.38
    beach
    0.37
    ラップ
    0.37
     mniej
    0.36
    బడి
    0.36
    Activations Density 0.001%

    No Known Activations