© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14258
    Prev
    Next
    INDEX
    Explanations

    technical writing related to chemistry and reactions and graphs.

    oai_token-act-pair · gemini-2.0-flash

    scientific language

    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
     CreateTagHelper
    -0.94
     betweenstory
    -0.81
    __':
    -0.76
    
    -0.75
    ValueStyle
    -0.74
    IUrlHelper
    -0.69
     NSCoder
    -0.68
    ftagPool
    -0.67
    RenderAtEndOf
    -0.67
    LookAnd
    -0.66
    POSITIVE LOGITS
     Sun
    0.48
    sego
    0.48
     Royal
    0.44
     M
    0.44
    IBUS
    0.42
    lucene
    0.42
     Фа
    0.41
    Royal
    0.41
     MI
    0.41
     заре
    0.41
    Activations Density 1.552%

    No Known Activations