© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13370
    Prev
    Next
    INDEX
    Explanations

    references to numbers of games in a row and ranking

    oai_token-act-pair · gemini-2.0-flash

    Sports records and statistics

    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
    dinga
    -0.63
     nakalista
    -0.57
    RUnlock
    -0.56
    IntoConstraints
    -0.55
     Names
    -0.51
     toga
    -0.51
    reportWebVitals
    -0.51
     Tinggi
    -0.49
    adaptiveStyles
    -0.48
    êques
    -0.47
    POSITIVE LOGITS
    <?
    0.56
    /**
    0.53
     weekends
    0.50
     summers
    0.49
    Przypisy
    0.49
     wins
    0.48
     affairs
    0.48
    leih
    0.48
    StringLength
    0.47
    FileChooser
    0.46
    Activations Density 2.225%

    No Known Activations