© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8574
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the possibility of customer interaction, such as requests, questions, or issues with an order

    oai_token-act-pair · gemini-2.0-flash

    technical terms or computer-related jargon

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

    contact information requests

    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
    .*")]
    -0.52
    GEBURTS
    -0.48
    JsonProperty
    -0.47
    atown
    -0.47
    茸
    -0.47
    ijas
    -0.46
     Wildcats
    -0.46
     gql
    -0.45
    רושלים
    -0.45
    μβρίου
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.74
     gepubliceerd
    0.70
    expandindo
    0.69
    oredCriteria
    0.63
    SharedDtor
    0.62
    sizeCache
    0.56
    thâu
    0.55
    esez
    0.54
     MenuView
    0.54
    دانشنامهٔ
    0.53
    Activations Density 1.142%

    No Known Activations