© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13944
    Prev
    Next
    INDEX
    Explanations

    mentions of data and numbers, particularly in a financial context.

    oai_token-act-pair · gemini-2.0-flash

    figure and figures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     traccia
    -0.51
     producteurs
    -0.44
    AddTagHelper
    -0.43
     connus
    -0.42
     défis
    -0.41
     pauvres
    -0.40
     direzione
    -0.40
    거
    -0.40
    ुक
    -0.40
     Tomaten
    -0.40
    POSITIVE LOGITS
     figure
    3.27
     figures
    3.16
    figure
    2.78
    figures
    2.75
     Figures
    2.61
     FIGURES
    2.36
    Figures
    2.28
     Figure
    2.25
     FIGURE
    2.20
     fig
    2.14
    Activations Density 4.952%

    No Known Activations