© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3971
    Prev
    Next
    INDEX
    Explanations

    various topics including: opinions, health, commerce, product features, code development, parenting, medical conditions, restaurants and stock trading.

    oai_token-act-pair · gemini-2.0-flash

    sealing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    BASEPATH
    -0.59
    PRNewswire
    -0.53
     ạ
    -0.51
     Theore
    -0.49
     important
    -0.47
    payee
    -0.47
    าก
    -0.46
    cieux
    -0.44
     bibliographical
    -0.44
    RenderAtEndOf
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.93
    IntoConstraints
    0.84
     autorytatywna
    0.71
    aarrggbb
    0.68
     AssemblyProduct
    0.65
     ModelExpression
    0.65
     виправивши
    0.64
     "..\..\..\
    0.64
    IUrlHelper
    0.62
     tartalomajánló
    0.60
    Activations Density 6.676%

    No Known Activations