© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12158
    Prev
    Next
    INDEX
    Explanations

    information about sports games and competition

    oai_token-act-pair · gemini-2.0-flash

    sporting matches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    stdio
    -0.57
     dug
    -0.54
     gig
    -0.54
     TextAppearance
    -0.53
    gig
    -0.52
     gigs
    -0.52
     gehe
    -0.49
    [+
    -0.49
    SequentialGroup
    -0.49
    Shir
    -0.48
    POSITIVE LOGITS
     facie
    0.56
    <bos>
    0.55
    oOo
    0.51
    Nuorodos
    0.48
    UnsafeEnabled
    0.47
    ミナル
    0.47
    tagHelperRunner
    0.47
    getActiveSheet
    0.47
    ————————————
    0.47
    MigrationBuilder
    0.47
    Activations Density 25.402%

    No Known Activations