© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10054
    Prev
    Next
    INDEX
    Explanations

    the word "in" and words next to it such as "an".

    oai_token-act-pair · gemini-2.0-flash

    an/in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     attempting
    -0.69
    Билгалдахарш
    -0.69
     essa
    -0.66
    webElementXpaths
    -0.65
     спро
    -0.64
    attempts
    -0.61
    Attempt
    -0.60
     attempted
    -0.60
     attempts
    -0.59
     "..\..\..\
    -0.59
    POSITIVE LOGITS
     an
    1.68
     bid
    1.05
    an
    1.01
    An
    0.85
     try
    0.84
     Try
    0.80
    Try
    0.77
    Bid
    0.73
     An
    0.70
    try
    0.69
    Activations Density 2.004%

    No Known Activations