© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35267
    Prev
    Next
    INDEX
    Explanations

    mixed language structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ༥
    0.41
    柢
    0.40
    ويت
    0.39
     혼
    0.39
    霍
    0.38
    ミック
    0.37
    蝰
    0.37
    砒
    0.37
    hoff
    0.37
    Hoist
    0.36
    POSITIVE LOGITS
    DAO
    0.44
     DAO
    0.43
     BS
    0.41
     Kv
    0.41
     bird
    0.39
    bird
    0.38
     Nombre
    0.37
     entrepreneur
    0.36
    right
    0.36
     unknown
    0.36
    Activations Density 0.000%

    No Known Activations