© 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. 9994
    Prev
    Next
    INDEX
    Explanations

    citations and references, specifically looking for punctuation, numbers, and formatting common in academic citations

    oai_token-act-pair · gemini-2.0-flash

    (

    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
    Datuak
    -0.56
    ".
    -0.55
    цездатний
    -0.54
     itſelf
    -0.54
    nikami
    -0.53
    tır
    -0.52
     againſt
    -0.52
    @[+][
    -0.52
     whoſe
    -0.51
    $.
    -0.51
    POSITIVE LOGITS
     Reverso
    0.56
    Encyclo
    0.55
    viaf
    0.54
    SequentialGroup
    0.54
    JHEP
    0.53
    BagConstraints
    0.52
     Pulitzer
    0.52
     Bioinformatics
    0.52
    aug
    0.50
    tagext
    0.49
    Activations Density 13.396%

    No Known Activations