© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6506
    Prev
    Next
    INDEX
    Explanations

    references to laws, acts, bills, and legal processes.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    NewUrlParser
    -0.58
    ecco
    -0.53
     pageContext
    -0.52
     tyn
    -0.50
    \{\\
    -0.50
    orite
    -0.49
    addCriterion
    -0.48
    gnition
    -0.48
    expandindo
    -0.46
    zili
    -0.46
    POSITIVE LOGITS
    ırken
    0.58
     cérami
    0.55
     nød
    0.54
    stateProvider
    0.54
    IndentedString
    0.53
    PHONY
    0.51
     ویکی‌آمباردا
    0.51
     colorés
    0.48
    ControllerTest
    0.48
     Operations
    0.48
    Activations Density 1.986%

    No Known Activations