© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10872
    Prev
    Next
    INDEX
    Explanations

    angle brackets and punctuation in computer code

    oai_token-act-pair · gemini-2.0-flash

    Less than sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     ddelweddau
    -0.66
     оригіналу
    -0.66
    Geplaatst
    -0.64
    atég
    -0.62
     diure
    -0.61
    antası
    -0.60
     Ephe
    -0.60
    farin
    -0.59
     فريبيس
    -0.58
    wahati
    -0.58
    POSITIVE LOGITS
    StoryboardSegue
    0.59
    Parcelize
    0.46
    (!__
    0.45
    <eos>
    0.45
     sé
    0.45
    :
    0.44
    ANTLR
    0.43
     an
    0.42
    assertEquals
    0.41
     opérés
    0.41
    Activations Density 1.505%

    No Known Activations