© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14978
    Prev
    Next
    INDEX
    Explanations

    various markers for computer code

    oai_token-act-pair · gemini-2.0-flash

    code and files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IntoConstraints
    -0.99
     étoient
    -0.94
    ⓧ
    -0.92
     élas
    -0.91
     avoient
    -0.88
     auroit
    -0.87
     chré
    -0.85
     feroit
    -0.84
     étoit
    -0.83
     normaux
    -0.83
    POSITIVE LOGITS
    :
    0.24
    gink
    0.23
    offsetTop
    0.23
    <bos>
    0.22
     to
    0.22
     kayak
    0.22
    ”),
    0.21
    kendo
    0.21
    ”)
    0.21
     posY
    0.21
    Activations Density 0.581%

    No Known Activations