© 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. 1440
    Prev
    Next
    INDEX
    Explanations

    instances of article/preposition/conjunction followed by a number

    oai_token-act-pair · gemini-2.0-flash

    Scientific writing and code

    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
     lī
    -0.64
     resourceCulture
    -0.63
     reine
    -0.54
     IMPLIED
    -0.52
     Waray
    -0.52
    出版年
    -0.51
    TagNumber
    -0.51
    XMLSchema
    -0.51
    ionales
    -0.50
    WindowConstants
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.56
    новништво
    0.56
    multer
    0.49
    delmi
    0.47
     Onion
    0.47
     Cu
    0.47
     onion
    0.45
     Salty
    0.45
     ReSharper
    0.45
    ArgsConstructor
    0.44
    Activations Density 2.629%

    No Known Activations