© 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. 10679
    Prev
    Next
    INDEX
    Explanations

    mentions of results from studies or facts that have been stated

    oai_token-act-pair · gemini-2.0-flash

    say "that"

    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
    awtextra
    -0.92
    ConstraintMaker
    -0.91
     мәкалә
    -0.82
     GenerationType
    -0.81
    httphttps
    -0.78
    OrNil
    -0.75
    ValueStyle
    -0.73
    this
    -0.73
     <=",
    -0.72
    MessageOf
    -0.72
    POSITIVE LOGITS
     that
    2.52
     That
    0.80
     dass
    0.78
     que
    0.75
    that
    0.74
     że
    0.71
     bahwa
    0.69
     että
    0.64
     что
    0.62
    That
    0.61
    Activations Density 1.253%

    No Known Activations