© 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. 14143
    Prev
    Next
    INDEX
    Explanations

    vamos analisar

    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
    潞
    0.37
    ρα
    0.35
    遊戲
    0.34
     特許庁
    0.34
    ΡΑ
    0.33
     caos
    0.33
     Palin
    0.33
     FURN
    0.32
     zá
    0.32
    lim
    0.32
    POSITIVE LOGITS
    Ï
    0.40
    نيه
    0.40
     Torch
    0.39
     bith
    0.39
     smartphone
    0.39
    Sug
    0.38
    doch
    0.38
    DispatchRequest
    0.38
     Caf
    0.37
    AMENTO
    0.37
    Activations Density 0.027%

    No Known Activations