© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4819
    Prev
    Next
    INDEX
    Explanations

    words related to amounts, percentages, improvement, application, and obligation, often within a technical or conversational context

    oai_token-act-pair · gemini-2.0-flash

    comparisons and analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AddTagHelper
    -0.71
    VIAF
    -0.68
    
    -0.67
    AddHtmlAttribute
    -0.65
    ьаж
    -0.63
     ligiloj
    -0.63
    UnknownFields
    -0.57
    ticles
    -0.57
     IconData
    -0.57
    ınd
    -0.55
    POSITIVE LOGITS
     propOrder
    0.48
    Опис
    0.47
    ///</
    0.46
     _$
    0.45
     wikipagina
    0.45
     dAtA
    0.44
     pobres
    0.43
     ***!
    0.42
     directeur
    0.42
     hello
    0.42
    Activations Density 9.740%

    No Known Activations