© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3706
    Prev
    Next
    INDEX
    Explanations

    code snippets related to centering images or using external modules in a program

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ja
    -0.69
     S
    -0.63
     C
    -0.61
     il
    -0.61
     for
    -0.60
     J
    -0.60
     /
    -0.59
     wy
    -0.58
    then
    -0.58
     also
    -0.58
    POSITIVE LOGITS
     itſelf
    1.13
    />";
    1.13
     Shakspeare
    1.07
     myſelf
    1.03
    ſelves
    1.02
    ')));
    1.01
     purpoſe
    1.00
    ſelf
    0.99
    ."));
    0.99
     themſelves
    0.98
    Activations Density 0.205%

    No Known Activations