© 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-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11913
    Prev
    Next
    INDEX
    Explanations

    mentions of a sports team, especially football, along with personnel and the year.

    oai_token-act-pair · gemini-2.0-flash

    Sports teams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.67
    MultipartFile
    -0.58
     متعلقه
    -0.58
     lenker
    -0.54
     extranjeros
    -0.53
     rospy
    -0.53
     arşivlendi
    -0.52
    хьтан
    -0.52
    mögens
    -0.50
     poveznice
    -0.50
    POSITIVE LOGITS
     समीक्षक
    0.62
    StoryboardSegue
    0.59
    ")));
    0.56
    HtmlAttribute
    0.56
     дописавши
    0.54
    "]));
    0.54
    RuleContext
    0.53
    fjspx
    0.52
     Fordham
    0.51
    colazione
    0.51
    Activations Density 1.952%

    No Known Activations