© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9557
    Prev
    Next
    INDEX
    Explanations

    phrases comparing quantities or amounts

    oai_token-act-pair · gemini-2.0-flash

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     than
    -1.27
    <bos>
    -1.09
     THAN
    -0.87
    Than
    -0.86
     niż
    -0.81
    than
    -0.80
     Than
    -0.77
    жели
    -0.72
     kuin
    -0.68
     ujednoznacz
    -0.66
    POSITIVE LOGITS
    ılacak
    0.55
    TabIndex
    0.55
    CreateModel
    0.54
    demie
    0.54
    PageRoute
    0.54
    Архівовано
    0.52
    प्त
    0.52
     Attend
    0.51
    UIControlState
    0.51
    MENAFN
    0.50
    Activations Density 2.141%

    No Known Activations