© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10454
    Prev
    Next
    INDEX
    Explanations

    strings of capital letters, especially related to programming or file formats, and acronyms including "DL" and "ML"

    oai_token-act-pair · gemini-2.0-flash

    System configurations and regulations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -0.63
     continúas
    -0.57
    Bibliografia
    -0.56
    Biographie
    -0.55
    ]]=
    -0.53
    latin
    -0.52
    lest
    -0.49
    quiao
    -0.49
    lur
    -0.47
    GeneratedMessage
    -0.46
    POSITIVE LOGITS
    addCriterion
    0.62
     متعلقه
    0.59
    ogical
    0.52
    ong
    0.52
     Monfieur
    0.51
     pleaſure
    0.50
     itſelf
    0.49
     Shee
    0.49
    CloseOperation
    0.48
     صوتيه
    0.48
    Activations Density 2.346%

    No Known Activations