© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2903
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate opinions or evaluations

    oai_token-act-pair · gemini-2.0-flash

    Long and complex sentences

    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
     AssemblyCulture
    -0.62
    <bos>
    -0.57
     mobilya
    -0.52
     sprend
    -0.51
     keç
    -0.51
     yazılı
    -0.49
     clube
    -0.48
     sını
    -0.47
     desenli
    -0.47
     baskılı
    -0.47
    POSITIVE LOGITS
    ,
    1.64
    ,...
    0.63
    RectangleBorder
    0.60
    ,…
    0.59
     most
    0.56
    oredCriteria
    0.56
    ,-,
    0.55
     Chwiliwch
    0.54
     CreateTagHelper
    0.51
    aderie
    0.51
    Activations Density 9.161%

    No Known Activations