© 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. 12831
    Prev
    Next
    INDEX
    Explanations

    snippets of mathematical LaTex code

    oai_token-act-pair · gemini-2.0-flash

    Mathematical/statistical context

    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
    +#+#
    -1.36
    awtextra
    -1.26
    LookAnd
    -1.20
     للمعارف
    -1.14
    windowFixed
    -1.13
    DockStyle
    -1.13
     فريبيس
    -1.13
    fromnode
    -1.13
    脚注の使い方
    -1.05
     للاسماء
    -1.05
    POSITIVE LOGITS
     
    0.60
     together
    0.50
    .
    0.48
     up
    0.48
    ,
    0.47
     U
    0.44
     S
    0.44
     $
    0.44
     made
    0.44
     in
    0.42
    Activations Density 7.711%

    No Known Activations