© 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. 12029
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "even" and often a negative word like "not".

    oai_token-act-pair · gemini-2.0-flash

    even

    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
    <eos>
    -0.50
    ต่างๆ
    -0.46
     aikana
    -0.43
    M
    -0.43
    "}";
    -0.42
    ండి
    -0.42
    didSet
    -0.41
     számára
    -0.41
     elettrica
    -0.41
     Mission
    -0.40
    POSITIVE LOGITS
    TintMode
    1.08
    WithIOException
    0.75
     kasarigan
    0.75
     >=",
    0.70
    Демографія
    0.69
     disambiguazione
    0.69
     Infórmanos
    0.69
     المعيارى
    0.68
    tagHelperRunner
    0.67
     متعلقه
    0.67
    Activations Density 0.321%

    No Known Activations