© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6576
    Prev
    Next
    INDEX
    Explanations

    the start of a description of related art examples.

    oai_token-act-pair · gemini-2.0-flash

    specific technical or complex terms

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

    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_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
     poussière
    -0.65
     ambientales
    -0.56
     bailando
    -0.52
     tensão
    -0.52
    脚注の使い方
    -0.52
     vaih
    -0.52
     jotka
    -0.51
     levure
    -0.51
     frutto
    -0.51
     vicenda
    -0.50
    POSITIVE LOGITS
     متعلقه
    0.70
     كومونز
    0.64
     Beſ
    0.56
    aarrggbb
    0.54
     contemporaneous
    0.54
    >\<^
    0.53
    LabelTagHelper
    0.53
    proken
    0.52
    Autoritní
    0.52
    BagConstraints
    0.52
    Activations Density 2.297%

    No Known Activations