© 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. 8170
    Prev
    Next
    INDEX
    Explanations

    a mix of years, ordinal numbers, and other numeric quantities with the words surrounding them also sometimes activating

    oai_token-act-pair · gemini-2.0-flash

    Digits

    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
     سكانية
    -0.66
    atelle
    -0.60
     дописавши
    -0.59
     therewith
    -0.50
    nades
    -0.49
     an
    -0.49
     Aps
    -0.48
    herit
    -0.47
     way
    -0.47
     (\<
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.88
    AddTagHelper
    0.73
    twimg
    0.59
    orcid
    0.55
    SequentialGroup
    0.55
    stdarg
    0.53
    devamını
    0.52
    webElementGuid
    0.52
    AndEndTag
    0.52
    of
    0.51
    Activations Density 8.514%

    No Known Activations