© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13342
    Prev
    Next
    INDEX
    Explanations

    the word "len" or instances of len() in code, or possibly words related to time

    oai_token-act-pair · gemini-2.0-flash

    len

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Conſ
    -0.91
    <bos>
    -0.90
     Monfieur
    -0.87
     Houſe
    -0.86
     Perſ
    -0.80
     Efq
    -0.78
     Inſ
    -0.76
     Reſ
    -0.74
     Diſ
    -0.71
     himſelf
    -0.71
    POSITIVE LOGITS
     rhestr
    0.69
    aarrggbb
    0.59
     Halen
    0.57
    redge
    0.57
     '\\;'
    0.57
    featureID
    0.56
     ocurrido
    0.56
     Spisak
    0.55
    теризу
    0.55
    aliana
    0.54
    Activations Density 2.700%

    No Known Activations