© 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. 7351
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    oai_token-act-pair · gemini-2.0-flash

    disjointed punctuation and casual phrases

    np_token-act-pair-logits · gpt-4o-mini
    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
     pinulongan
    -0.84
    twimg
    -0.77
     Wikimedijinoj
    -0.72
    zzleHttp
    -0.72
     propOrder
    -0.71
     Unsc
    -0.68
    apimachinery
    -0.67
    BASEPATH
    -0.67
     noqa
    -0.67
     архивлан
    -0.67
    POSITIVE LOGITS
    fromnode
    0.49
    ROIT
    0.39
    bench
    0.39
     dignidad
    0.38
    こんにちは
    0.37
    AND
    0.36
     infine
    0.36
    f
    0.35
    court
    0.35
    looking
    0.35
    Activations Density 0.856%

    No Known Activations