© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4755
    Prev
    Next
    INDEX
    Explanations

    the word "output" in a block of code

    oai_token-act-pair · gemini-2.0-flash

    output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     output
    -2.78
    output
    -2.58
     Output
    -2.48
    Output
    -2.44
     OUTPUT
    -2.17
     outputs
    -2.17
    OUTPUT
    -1.98
     Outputs
    -1.87
    输出
    -1.82
    outputs
    -1.65
    POSITIVE LOGITS
    wait
    0.48
    วัติ
    0.46
    reh
    0.46
     Dang
    0.45
    ViewHolder
    0.45
     Wait
    0.45
    antaranya
    0.45
     Press
    0.45
    velo
    0.45
    kuli
    0.45
    Activations Density 0.689%

    No Known Activations