© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9372
    Prev
    Next
    INDEX
    Explanations

    proper nouns ending in "by" or "combe" as well as the word "full"

    oai_token-act-pair · gemini-2.0-flash

    football/gene mutations

    np_max-act · 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
    Negative Logits
     مرئيه
    -0.67
    topf
    -0.65
     Romains
    -0.63
    はじめに
    -0.60
    racer
    -0.60
    aziland
    -0.60
     SwitchCompat
    -0.59
     klok
    -0.59
    Tracer
    -0.58
    NewLabel
    -0.57
    POSITIVE LOGITS
     NSCoder
    0.70
    abank
    0.61
    abestanden
    0.60
     وتسجيلات
    0.60
    ImageContext
    0.59
    RepeatedField
    0.59
    ?\\
    0.55
    .",
    0.55
    لاث
    0.54
    \}\\
    0.54
    Activations Density 0.239%

    No Known Activations