© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3287
    Prev
    Next
    INDEX
    Explanations

    math and code symbols like brackets and functions alongside some capitalized words

    oai_token-act-pair · gemini-2.0-flash

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     [
    -0.75
    [
    -0.65
     $[
    -0.60
    MENAFN
    -0.59
    [
    -0.56
    ()[
    -0.56
     ([
    -0.55
    $[
    -0.54
    }=[
    -0.54
     [[
    -0.54
    POSITIVE LOGITS
    tagHelperRunner
    0.68
    SerializedName
    0.66
     contextLoads
    0.65
    abstractmethod
    0.59
    VersionUID
    0.59
     GetEnumerator
    0.58
     ModelExpression
    0.57
    StoryboardSegue
    0.56
    MMdd
    0.56
    colgroup
    0.55
    Activations Density 16.755%

    No Known Activations