© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10942
    Prev
    Next
    INDEX
    Explanations

    code related notations like special characters and names of common code commands

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tagHelper
    -1.51
    DatabaseError
    -0.61
     (
    -0.50
    AuthContext
    -0.50
     N
    -0.50
     BoxFit
    -0.49
    اغ
    -0.49
     so
    -0.48
     RoutedEventArgs
    -0.48
     L
    -0.48
    POSITIVE LOGITS
     itſelf
    1.09
     myſelf
    0.93
     poffible
    0.90
     Monfieur
    0.88
     faſt
    0.86
     houſe
    0.85
     Houſe
    0.85
    ſelf
    0.82
     leſs
    0.81
    neſs
    0.80
    Activations Density 0.021%

    No Known Activations