© 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. 10329
    Prev
    Next
    INDEX
    Explanations

    test code assertions

    oai_token-act-pair · gemini-2.0-flash

    potential language structures or patterns

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

    )

    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
     Ben
    -0.46
    ∬
    -0.45
     mit
    -0.45
    拌
    -0.44
     Built
    -0.44
     S
    -0.43
    ({})
    -0.43
    עם
    -0.42
    liato
    -0.42
    ubung
    -0.42
    POSITIVE LOGITS
     leaſt
    0.77
     Houſe
    0.71
     Anſ
    0.71
     Reſ
    0.70
    ExecuteReader
    0.69
     poffe
    0.68
    ſelves
    0.67
     Majefty
    0.66
     houſe
    0.66
    addCriterion
    0.65
    Activations Density 0.891%

    No Known Activations