© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    technical language used in scientific research papers, including numerical values, units of measure, and references to figures and tables

    oai_token-act-pair · gemini-2.0-flash

    scientific datasets

    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
    +#+
    -0.67
     Efq
    -0.60
    دانشنامهٔ
    -0.59
    AsUp
    -0.58
     geene
    -0.58
    ofire
    -0.56
    PullParser
    -0.56
    VersionUID
    -0.56
    complexContent
    -0.56
    interopRequire
    -0.56
    POSITIVE LOGITS
     \\
    0.41
    W
    0.41
    Cg
    0.40
    0
    0.39
     către
    0.39
    he
    0.38
    γ
    0.37
     \
    0.37
    µ
    0.36
    isotope
    0.35
    Activations Density 21.115%

    No Known Activations