© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10855
    Prev
    Next
    INDEX
    Explanations

    the word "several" or related words indicating quantity like "couple", "numerous", or "many".

    oai_token-act-pair · gemini-2.0-flash

    several

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    several
    -0.69
     Several
    -0.68
     several
    -0.68
    Several
    -0.68
    Numerous
    -0.60
     beberapa
    -0.59
     několika
    -0.58
     Numerous
    -0.57
     flera
    -0.56
     numerous
    -0.54
    POSITIVE LOGITS
    saraba
    0.65
    tagext
    0.63
     truths
    0.63
    期刊论文
    0.62
    Erreferentziak
    0.61
     strands
    0.60
    Portale
    0.60
    webElementXpaths
    0.60
     exceptions
    0.59
     subspecies
    0.59
    Activations Density 2.950%

    No Known Activations