© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12532
    Prev
    Next
    INDEX
    Explanations

    words and punctuation appearing in medical texts that contain statistical information.

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    tagHelperRunner
    -1.13
    AndEndTag
    -0.93
    ScopeManager
    -0.84
    Portail
    -0.79
    Brainz
    -0.77
     تضيفلها
    -0.76
    RegressionTest
    -0.75
    MethodManager
    -0.74
    Rhestr
    -0.73
     ModelExpression
    -0.73
    POSITIVE LOGITS
     Central
    0.46
     M
    0.41
     T
    0.41
    optString
    0.41
     Dan
    0.41
    ogel
    0.40
     soir
    0.40
     modern
    0.40
     Bu
    0.40
     W
    0.40
    Activations Density 1.669%

    No Known Activations