© 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. 14806
    Prev
    Next
    INDEX
    Explanations

    percentages of things

    oai_token-act-pair · gemini-2.0-flash

    mathematical percentages and financial terms

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

    Percentages

    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
     للاسماء
    -1.05
     Signalez
    -1.00
     Paglinawan
    -0.98
     '\\;'
    -0.94
    RenderAtEndOf
    -0.93
    PyExc
    -0.93
    featureID
    -0.92
    findpost
    -0.91
    SequentialGroup
    -0.91
     estekak
    -0.84
    POSITIVE LOGITS
     of
    0.78
    le
    0.54
     le
    0.51
     or
    0.48
     d
    0.47
     word
    0.46
    ant
    0.45
     in
    0.44
     L
    0.44
     max
    0.44
    Activations Density 8.617%

    No Known Activations