© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 33815
    Prev
    Next
    INDEX
    Explanations

    American football players

    np_max-act-logits · gemini-2.5-flash-lite

    information related to NFL MVP winners and their career status.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    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
    stances
    0.43
    𝑋
    0.41
    Symbol
    0.38
     leaked
    0.38
    FieldValue
    0.37
     leaky
    0.37
    レイン
    0.37
    symbol
    0.37
    𝑡
    0.37
    劳动
    0.36
    POSITIVE LOGITS
    жерела
    0.48
     megsz
    0.39
     KEN
    0.39
    roskop
    0.39
     Jacinto
    0.39
     Argent
    0.39
     Zariski
    0.38
    iroz
    0.38
     Kad
    0.37
     Pop
    0.37
    Activations Density 0.001%

    No Known Activations