© 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. 10480
    Prev
    Next
    INDEX
    Explanations

    the phrase "there are so many"

    oai_token-act-pair · gemini-2.0-flash

    say "many" and "much"

    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
    extAlignment
    -0.69
    ToAction
    -0.69
     ویکی‌پدیای
    -0.66
    Fordítás
    -0.62
     defStyleAttr
    -0.62
     kaban
    -0.60
    ücksich
    -0.59
     nghiệp
    -0.58
     greateſt
    -0.58
     Himmels
    -0.57
    POSITIVE LOGITS
    TagMode
    0.61
     AspNetCore
    0.53
    şiv
    0.50
     autorytatywna
    0.49
    createCanvas
    0.44
    RTEX
    0.44
    complexContent
    0.43
    MemoryWarning
    0.41
    writeFieldEnd
    0.40
     Sneak
    0.40
    Activations Density 1.246%

    No Known Activations