© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11992
    Prev
    Next
    INDEX
    Explanations

    mentions of eyes, brain hemispheres, and related medical conditions and terminology

    oai_token-act-pair · gemini-2.0-flash

    eyes

    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
     Efq
    -1.31
     Theſe
    -1.23
     Shakspeare
    -1.19
     Jefus
    -1.16
     myſelf
    -1.16
     ſeveral
    -1.05
     becauſe
    -1.02
     whoſe
    -1.02
     pleaſure
    -1.01
     Majefty
    -1.00
    POSITIVE LOGITS
     of
    0.48
     (
    0.47
     it
    0.46
    .
    0.46
    it
    0.45
     B
    0.44
     P
    0.44
    ,
    0.44
     so
    0.42
    P
    0.40
    Activations Density 2.215%

    No Known Activations