© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15076
    Prev
    Next
    INDEX
    Explanations

    negations in sentences.

    oai_token-act-pair · gemini-2.0-flash

    Technical/programming context

    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
     Less
    -0.53
     Safe
    -0.52
     less
    -0.52
    OLVED
    -0.51
    Clik
    -0.51
     Maybe
    -0.50
    obo
    -0.49
    éa
    -0.49
     safe
    -0.49
     menos
    -0.49
    POSITIVE LOGITS
     OnDestroy
    0.79
    FormTagHelper
    0.71
    BeginContext
    0.69
    ContentAsync
    0.65
    PostConstruct
    0.63
     CreateTagHelper
    0.62
    <>();
    0.60
    "?>
    0.60
     dependencia
    0.60
     ویکی‌آمباردا
    0.60
    Activations Density 2.570%

    No Known Activations