© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1652
    Prev
    Next
    INDEX
    Explanations

    scientific documents that use Greek letters and Latin abbreviations when describing laboratory experiments

    oai_token-act-pair · gemini-2.0-flash

    beta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    dev
    -0.85
     Pilot
    -0.76
    Pilot
    -0.71
     pilot
    -0.71
    enumi
    -0.71
    Dev
    -0.69
     dev
    -0.68
    pilot
    -0.66
    migrationBuilder
    -0.65
    SourceChecksum
    -0.64
    POSITIVE LOGITS
    ReusableCell
    0.50
    AutoField
    0.46
     jadx
    0.45
    onActivityResult
    0.44
    بوابة
    0.44
    verick
    0.43
    Revenir
    0.43
     هنا
    0.43
    currentTarget
    0.42
    
    0.41
    Activations Density 9.984%

    No Known Activations