© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4184
    Prev
    Next
    INDEX
    Explanations

    dialogue or quoted text, especially when marked by quotation marks and other punctuation

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     تضيفلها
    -0.82
     CreateTagHelper
    -0.66
    OGND
    -0.64
    elemField
    -0.59
     Waray
    -0.58
    Tracce
    -0.57
    KommentareTeilen
    -0.55
     FBref
    -0.55
    كويكب
    -0.54
     Rande
    -0.54
    POSITIVE LOGITS
     Италијани
    0.53
     Zhang
    0.50
    RICAL
    0.49
     Baillargeon
    0.48
     Liu
    0.48
    duff
    0.47
    Specyfikacja
    0.47
    ỳnh
    0.46
     CWE
    0.46
    sprecher
    0.45
    Activations Density 0.586%

    No Known Activations