© 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. 1934
    Prev
    Next
    INDEX
    Explanations

    greetings, farewells, and general conversational language for online forums

    oai_token-act-pair · gemini-2.0-flash

    start of emails/posts

    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
     surla
    -0.58
    <bos>
    -0.58
    SequentialGroup
    -0.57
    SourceChecksum
    -0.53
     بيها
    -0.52
    wości
    -0.52
    kegaard
    -0.52
     Affecting
    -0.48
     VIAF
    -0.47
     propOrder
    -0.47
    POSITIVE LOGITS
    */].
    0.60
     last
    0.60
     could
    0.60
     great
    0.55
     do
    0.55
     برانيه
    0.52
    icle
    0.52
    RectangleBorder
    0.52
     Last
    0.51
     its
    0.50
    Activations Density 9.220%

    No Known Activations