© 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. 10564
    Prev
    Next
    INDEX
    Explanations

    strings of digits, especially formatted as numbers or codes

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or unusual formatting

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

    digits

    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
    SizeMode
    -0.63
     useAppContext
    -0.61
    nmgp
    -0.57
    InstrumentedTest
    -0.56
    cshtml
    -0.54
    ิ่ม
    -0.53
     EconPapers
    -0.52
     /\.(
    -0.52
    jsdelivr
    -0.50
    vada
    -0.50
    POSITIVE LOGITS
     Theſe
    0.62
     myſelf
    0.57
    SerializedSize
    0.56
     becauſe
    0.55
     itſelf
    0.54
     purpoſe
    0.54
    帖最后由
    0.53
    ValueStyle
    0.53
     pleaſure
    0.53
     raiſ
    0.52
    Activations Density 13.059%

    No Known Activations