© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8026
    Prev
    Next
    INDEX
    Explanations

    mentions of scoring in sports or testing

    oai_token-act-pair · gemini-2.0-flash

    scored

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    enderror
    -0.82
     el
    -0.68
    numerusform
    -0.63
     un
    -0.63
     a
    -0.62
     z
    -0.62
     ha
    -0.62
     und
    -0.61
     sal
    -0.60
     sto
    -0.59
    POSITIVE LOGITS
     Monfieur
    1.57
     Reſ
    1.47
     Houſe
    1.38
     myſelf
    1.38
     Anſ
    1.37
     Diſ
    1.34
     itſelf
    1.33
     Eſ
    1.33
     Theſe
    1.33
     Inſ
    1.31
    Activations Density 3.299%

    No Known Activations