© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5321
    Prev
    Next
    INDEX
    Explanations

    HTML code and blog post metadata

    oai_token-act-pair · gemini-2.0-flash

    Website code/documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    <h3>
    -0.85
    </h6>
    -0.69
    <h5>
    -0.66
    Földrajzportál
    -0.62
    LookAnd
    -0.61
    PerformLayout
    -0.60
    didSet
    -0.60
    ！』
    -0.58
    <h6>
    -0.57
    ？』
    -0.57
    POSITIVE LOGITS
    bootstrapcdn
    0.57
    imageshack
    0.53
    errHandler
    0.51
     onAnimation
    0.48
    cshtml
    0.47
    uhi
    0.44
    )))),
    0.44
     Chwiliwch
    0.44
     réf
    0.43
    看书
    0.43
    Activations Density 0.092%

    No Known Activations