© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14440
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused1896>
    0.17
    <unused1776>
    0.16
    <unused416>
    0.16
    <unused1741>
    0.16
    <unused331>
    0.16
    <unused709>
    0.16
    <unused299>
    0.16
    <unused315>
    0.16
    <unused348>
    0.16
    <unused1098>
    0.16
    POSITIVE LOGITS
    +
    0.23
     +
    0.23
    0.20
    =
    0.19
    /
    0.19
     (
    0.17
     is
    0.17
     =
    0.17
     -
    0.17
    2
    0.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.