© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11713
    Prev
    Next
    INDEX
    Explanations

    negations, especially the contraction "n't"

    oai_token-act-pair · gemini-2.0-flash

    t/not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    elog
    -0.51
     *}$
    -0.50
     never
    -0.50
     cannot
    -0.49
    ранее
    -0.48
     Fort
    -0.48
    τό
    -0.46
    什么意思
    -0.45
     asla
    -0.44
     Coach
    -0.44
    POSITIVE LOGITS
     Мексичка
    0.68
    ="@+
    0.67
    ($__
    0.60
    ArrowToggle
    0.59
    WebVitals
    0.59
     CURIAM
    0.58
    oa̍t
    0.57
    HasAnnotation
    0.57
     Besoin
    0.55
    tagHelperRunner
    0.54
    Activations Density 0.745%

    No Known Activations