© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8685
    Prev
    Next
    INDEX
    Explanations

    hedging and weasel words

    oai_token-act-pair · gemini-2.0-flash

    reports, measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Carriera
    -0.60
    AddColumn
    -0.49
    vably
    -0.49
     незавершена
    -0.48
     suffice
    -0.48
     torchvision
    -0.47
     tráng
    -0.47
    pædia
    -0.47
     Мексичка
    -0.44
    \}\\
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.66
    الإنجليزية
    0.65
     cherchés
    0.65
     nahilalakip
    0.63
     विश्वसनीयता
    0.60
     المعيارى
    0.60
    цездатний
    0.59
    تقاوى
    0.58
    windowFixed
    0.58
     '{@
    0.57
    Activations Density 0.623%

    No Known Activations