© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7966
    Prev
    Next
    INDEX
    Explanations

    text related to sports transfers and contracts

    oai_token-act-pair · gemini-2.0-flash

    Soccer/Sports News

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     myſelf
    -0.86
    ValueStyle
    -0.83
    ArrowToggle
    -0.82
     purpoſe
    -0.81
     ſame
    -0.80
     juſ
    -0.77
     houſe
    -0.77
     Efq
    -0.77
     uſe
    -0.76
     Perſ
    -0.76
    POSITIVE LOGITS
     imp
    0.46
     Thomas
    0.44
    Thomas
    0.44
     pre
    0.42
    dy
    0.41
     pul
    0.39
    cu
    0.37
     Bea
    0.37
    static
    0.37
     action
    0.37
    Activations Density 1.584%

    No Known Activations