© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10837
    Prev
    Next
    INDEX
    Explanations

    C code defining bitwise operations on bitfields related to RX_COALESCE

    oai_token-act-pair · gemini-2.0-flash

    gibberish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     CO
    -1.73
    Ko
    -1.69
     Ko
    -1.68
    CO
    -1.64
     Co
    -1.63
    Co
    -1.61
    Col
    -1.59
     Col
    -1.58
     COL
    -1.57
    COL
    -1.53
    POSITIVE LOGITS
    abestanden
    0.50
     Newberry
    0.46
     TLR
    0.46
    parsedMessage
    0.45
     Bentham
    0.45
     Jann
    0.44
    toMatchSnapshot
    0.43
     Lumière
    0.42
    GEBURTS
    0.42
    外部リンク
    0.41
    Activations Density 1.280%

    No Known Activations