© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14395
    Prev
    Next
    INDEX
    Explanations

    references to outside figures, tables, and other documents, using a variety of formats

    oai_token-act-pair · gemini-2.0-flash

    references to figures or tables

    np_token-act-pair-logits · gpt-4o-mini

    figure/table

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    戶
    -0.44
    ort
    -0.41
    kwds
    -0.40
     Bharat
    -0.39
     контра
    -0.39
     soins
    -0.38
     ProtoMessage
    -0.38
     Lel
    -0.37
    partimento
    -0.36
    bidden
    -0.36
    POSITIVE LOGITS
     figure
    1.59
     Figure
    1.37
    figure
    1.30
     FIGURE
    1.27
     figures
    1.27
     fig
    1.26
     table
    1.25
     Table
    1.25
    Figure
    1.23
    Table
    1.18
    Activations Density 7.528%

    No Known Activations