© 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. 13468
    Prev
    Next
    INDEX
    Explanations

    file paths and code installation instructions

    oai_token-act-pair · gemini-2.0-flash

    words related to programming or programming contexts

    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
    disambiguation
    -0.85
     ExecuteAsync
    -0.84
    Tembelea
    -0.79
    ніципалі
    -0.71
    InputTagHelper
    -0.67
    SequentialGroup
    -0.67
    dafx
    -0.66
     ModelExpression
    -0.66
    =$?
    -0.66
     Référence
    -0.65
    POSITIVE LOGITS
    Programa
    0.42
    ad
    0.41
     uç
    0.40
    my
    0.40
    前
    0.39
    jov
    0.38
    çoit
    0.38
     freely
    0.38
    end
    0.37
    Program
    0.37
    Activations Density 1.246%

    No Known Activations