© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    mentions of text encoding formats like UTF-8 and ASCII and other programming terms

    oai_token-act-pair · gemini-2.0-flash

    encoding formats and character sets

    np_token-act-pair-logits · gpt-4o-mini

    say character encoding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    .*")]
    -0.70
     iſt
    -0.70
    webElement
    -0.68
     Theſe
    -0.68
     Jefus
    -0.66
     itſelf
    -0.65
    Rè
    -0.65
     auffi
    -0.64
     fhort
    -0.63
    webElementXpaths
    -0.62
    POSITIVE LOGITS
    #
    0.50
    бок
    0.47
    IContainer
    0.43
    #[
    0.42
    Brainz
    0.41
    ตัว
    0.40
     #
    0.40
    lerinden
    0.40
    ýchod
    0.40
    E
    0.38
    Activations Density 1.582%

    No Known Activations