© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13659
    Prev
    Next
    INDEX
    Explanations

    a number after the article 'a' or after the preposition 'per'.

    oai_token-act-pair · gemini-2.0-flash

    Numerical data/time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Datuak
    -0.66
     nakalista
    -0.59
    AddTagHelper
    -0.57
    StreetMap
    -0.56
    MessageOf
    -0.56
    IntoConstraints
    -0.54
    RenderAtEndOf
    -0.54
    
    -0.54
     فريبيس
    -0.54
    protoimpl
    -0.53
    POSITIVE LOGITS
    dafx
    0.56
    CROSSTALK
    0.54
    Jîn
    0.52
    帖最后由
    0.50
    Externí
    0.50
     convertView
    0.49
     AssemblyProduct
    0.48
    Notae
    0.47
     Bid
    0.45
    pence
    0.45
    Activations Density 2.646%

    No Known Activations