© 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. 2971
    Prev
    Next
    INDEX
    Explanations

    a wide range of Latex math symbols in scientific documents and xcode interface elements

    oai_token-act-pair · gemini-2.0-flash

    math and code

    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
    AsUp
    -0.68
    __':
    -0.66
     itſelf
    -0.63
    __':
    -0.62
    RetentionPolicy
    -0.62
     comigo
    -0.60
     myſelf
    -0.60
    〢
    -0.60
     raiſ
    -0.59
    ^(@)
    -0.59
    POSITIVE LOGITS
    cshtml
    0.71
    ynb
    0.61
    AxisAlignment
    0.59
    ClientSize
    0.58
    jsdelivr
    0.57
    DateTimeField
    0.54
    PhysRevD
    0.52
     BoxDecoration
    0.50
     sockaddr
    0.49
    NCT
    0.48
    Activations Density 5.321%

    No Known Activations