© 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. 12659
    Prev
    Next
    INDEX
    Explanations

    seemingly random letter combinations

    oai_token-act-pair · gemini-2.0-flash

    patterns related to parsing and data structure errors

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

    code and errors

    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
     resourceCulture
    -0.68
    RegressionTest
    -0.61
    ніципалі
    -0.54
     nakalista
    -0.51
     يتيمه
    -0.51
    kins
    -0.51
    onete
    -0.50
     cherchés
    -0.50
    getConnection
    -0.48
    otimes
    -0.47
    POSITIVE LOGITS
    ff
    0.57
    uro
    0.56
    fastjson
    0.53
    URO
    0.50
     Вікіпе
    0.49
     Профиль
    0.49
    FF
    0.48
    CurrentValue
    0.48
    qu
    0.48
    xchange
    0.47
    Activations Density 4.450%

    No Known Activations