© 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. 5004
    Prev
    Next
    INDEX
    Explanations

    HTML markup tags and related terms

    oai_token-act-pair · gemini-2.0-flash

    HTML tags and syntax elements

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

    div

    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
    featureID
    -0.50
    tonsoft
    -0.50
     drôle
    -0.49
    ceğini
    -0.46
     oublié
    -0.45
     đình
    -0.45
     existir
    -0.43
    rungsseite
    -0.43
    tagext
    -0.42
    parsedMessage
    -0.41
    POSITIVE LOGITS
    </thead>
    0.74
     يتيمه
    0.73
    URLException
    0.69
     **/
    0.65
    ViewImports
    0.65
    enumi
    0.63
    </caption>
    0.63
    !")
    0.60
    !");
    0.59
     *
    0.58
    Activations Density 0.499%

    No Known Activations