© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5554
    Prev
    Next
    INDEX
    Explanations

    inequality symbols and related terms in mathematical notation and HTML

    oai_token-act-pair · gemini-2.0-flash

    Code and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -------------</
    -0.59
    ViewChild
    -0.58
    posedge
    -0.56
    (!__
    -0.56
    "]]
    -0.54
     JpaRepository
    -0.53
    itarianism
    -0.52
    TestingModule
    -0.52
    `
    -0.51
    ELTS
    -0.50
    POSITIVE LOGITS
    ;
    1.83
    ;
    1.29
    ;,
    1.22
    ;.
    1.21
    ；
    1.20
    ;}
    1.18
    ؛
    1.17
    ;\
    1.16
    ;&
    1.16
    ;(
    1.13
    Activations Density 2.957%

    No Known Activations