© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6695
    Prev
    Next
    INDEX
    Explanations

    figure references with captions

    oai_token-act-pair · gemini-2.0-flash

    closing brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    WindowConstants
    -0.64
     EconPapers
    -0.64
    ]")]
    -0.63
     tartalomajánló
    -0.61
    SequentialGroup
    -0.59
    mybatisplus
    -0.59
     Administrativna
    -0.59
     HttpNotFound
    -0.56
    findpost
    -0.56
    ).—
    -0.56
    POSITIVE LOGITS
    “[
    0.77
     $[
    0.67
     [
    0.64
    ([
    0.63
    ,[
    0.63
    .[
    0.57
     $[\
    0.56
    >[
    0.56
    [-
    0.56
    :[
    0.55
    Activations Density 2.203%

    No Known Activations