© 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. 9851
    Prev
    Next
    INDEX
    Explanations

    language related to arts, crafts, sewing, and selling items online

    oai_token-act-pair · gemini-2.0-flash

    specific programming or technical terms

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

    arts and crafts

    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
     getContent
    -0.50
     asing
    -0.44
     zengin
    -0.43
    znacz
    -0.41
     keş
    -0.40
     teor
    -0.40
     değişti
    -0.39
    tosis
    -0.39
    =@"
    -0.38
    getDriver
    -0.37
    POSITIVE LOGITS
    GEBURTSDATUM
    0.95
    StoryboardSegue
    0.93
     Мексичка
    0.91
    URLException
    0.82
    RenderAtEndOf
    0.82
    OrNil
    0.80
    verwijspagina
    0.77
    parsedMessage
    0.74
     propOrder
    0.74
    GraphicsUnit
    0.74
    Activations Density 6.622%

    No Known Activations