© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11474
    Prev
    Next
    INDEX
    Explanations

    the word "versus", and sometimes numbers or words near "versus"

    oai_token-act-pair · gemini-2.0-flash

    versus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .
    -0.91
    en
    -0.77
    o
    -0.74
    t
    -0.72
    y
    -0.71
    e
    -0.67
    a
    -0.65
    tro
    -0.64
    ten
    -0.63
    tes
    -0.63
    POSITIVE LOGITS
     réguli
    1.20
     démocr
    1.19
     abstrait
    1.18
     feroit
    1.15
     colorés
    1.14
     ModelExpression
    1.13
     chré
    1.12
     pouvoit
    1.12
     auroit
    1.10
     fermés
    1.10
    Activations Density 2.914%

    No Known Activations