© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13003
    Prev
    Next
    INDEX
    Explanations

    various special characters and the "di" prefix

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    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
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.56
    ]?.
    -0.54
     незавершена
    -0.52
    tiamo
    -0.50
     vender
    -0.50
    "])
    -0.49
     թվական
    -0.47
    TagMode
    -0.47
     vzor
    -0.47
     {.
    -0.46
    POSITIVE LOGITS
    OrBuilder
    0.73
    principalColumn
    0.69
    parametrize
    0.66
    UnsafeEnabled
    0.65
     StatelessWidget
    0.62
    fjspx
    0.62
    SaveChangesAsync
    0.62
    GEBURTS
    0.61
     مشين
    0.60
    SuppressLint
    0.60
    Activations Density 1.174%

    No Known Activations