© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose. Specifically, words that often relate to cause or reasons.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

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

    in

    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
    GraphicsUnit
    -0.68
     Exacts
    -0.68
     оригіналу
    -0.67
    PyExc
    -0.61
    httphttps
    -0.58
    amata
    -0.57
     تانيه
    -0.56
     resourceCulture
    -0.56
     Dider
    -0.52
    nationality
    -0.52
    POSITIVE LOGITS
    FieldNumber
    0.50
    CNP
    0.49
    URLException
    0.49
    StartTag
    0.47
     in
    0.45
     AssemblyTitle
    0.45
    ElementException
    0.45
     offert
    0.43
    parametrize
    0.41
    ModelSerializer
    0.41
    Activations Density 0.917%

    No Known Activations