© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11865
    Prev
    Next
    INDEX
    Explanations

    snippets of code related to property names, config, flags, meshes, or media type, regardless of coding language

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Nuorodos
    -0.56
    IntoConstraints
    -0.56
     dAtA
    -0.55
     FileWriter
    -0.54
     تضيفلها
    -0.52
    mergeFrom
    -0.52
    knecht
    -0.52
    AndEndTag
    -0.50
    FailureListener
    -0.50
    Hare
    -0.50
    POSITIVE LOGITS
     Meksiku
    0.63
    <bos>
    0.63
    stdc
    0.57
    Controllo
    0.54
    %">
    0.54
     PRINCIP
    0.52
    ',{
    0.51
    igerung
    0.51
    тьяна
    0.50
    );?>
    0.50
    Activations Density 8.466%

    No Known Activations