© 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. 8632
    Prev
    Next
    INDEX
    Explanations

    Javascript import statements and related syntax

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax

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

    Code

    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
    3
    -0.50
    id
    -0.43
    z
    -0.42
     beina
    -0.40
    2
    -0.40
    پایی
    -0.39
    `
    -0.39
    print
    -0.38
    ען
    -0.38
     <<<<<<<<<<<<<<
    -0.38
    POSITIVE LOGITS
     propOrder
    0.91
    OwnProperty
    0.77
     سكانية
    0.75
     >=",
    0.72
    ConstraintMaker
    0.69
     وتسجيلات
    0.67
     <=",
    0.67
     protoimpl
    0.66
    nodoc
    0.63
    DataAnnotations
    0.63
    Activations Density 0.225%

    No Known Activations