© 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. 8706
    Prev
    Next
    INDEX
    Explanations

    numbers related to data or statistics in research reports

    oai_token-act-pair · gemini-2.0-flash

    numerical values and their variations (like 'hundred', 'thousand')

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

    powers of ten

    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
     ten
    -0.68
     douze
    -0.65
     twelve
    -0.57
     thirteen
    -0.57
     eleven
    -0.56
     fifteen
    -0.56
     eight
    -0.56
     six
    -0.55
     five
    -0.55
     nine
    -0.54
    POSITIVE LOGITS
    CppMethod
    0.96
    EndGlobalSection
    0.94
     hundred
    0.93
    hundred
    0.89
     HUND
    0.85
     Hundred
    0.84
     thousand
    0.83
     hundreds
    0.79
     Thousand
    0.77
     thousands
    0.75
    Activations Density 3.599%

    No Known Activations