© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13865
    Prev
    Next
    INDEX
    Explanations

    phrases with function words, possibly mathematical symbols and some words that are related to law and order.

    oai_token-act-pair · gemini-2.0-flash

    Transitions between ideas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     виправивши
    -0.58
    izien
    -0.46
    емъ
    -0.45
    itattu
    -0.44
     existi
    -0.44
     tartalomajánló
    -0.42
    >({
    -0.42
    getTag
    -0.40
     trillion
    -0.40
     CreateTagHelper
    -0.40
    POSITIVE LOGITS
    ///</
    0.70
    <bos>
    0.69
    AndEndTag
    0.68
    లాలు
    0.68
     Wikimedijinoj
    0.66
    #
    0.63
    boutin
    0.62
    $_['
    0.61
    strconv
    0.60
    /*---
    0.60
    Activations Density 4.996%

    No Known Activations