© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9674
    Prev
    Next
    INDEX
    Explanations

    code snippets with bugs and a first-person response to the bug

    oai_token-act-pair · gemini-2.0-flash

    your/my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ്
    -0.42
     düş
    -0.41
    Sind
    -0.40
     tombé
    -0.39
     connues
    -0.39
     fatica
    -0.38
    Audiobook
    -0.38
     something
    -0.38
     laget
    -0.37
     modelAndView
    -0.36
    POSITIVE LOGITS
    الحياه
    0.76
     '\\;'
    0.74
     >=",
    0.73
    GEBURTSDATUM
    0.72
    URLException
    0.71
     unknownFields
    0.69
     مشين
    0.69
    OGND
    0.69
    AndEndTag
    0.68
    ništ
    0.67
    Activations Density 0.701%

    No Known Activations