© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6492
    Prev
    Next
    INDEX
    Explanations

    words and short phrases that negate an idea

    oai_token-act-pair · gemini-2.0-flash

    qualifiers indicating uncertainty

    np_token-act-pair-logits · gpt-4o-mini

    adverbs of certainty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     könnte
    -0.50
     möglicherweise
    -0.49
     mungkin
    -0.47
    fören
    -0.47
     geluk
    -0.46
    wikimedia
    -0.46
     gelieb
    -0.45
     ممکن
    -0.45
    createStatement
    -0.44
    igshid
    -0.42
    POSITIVE LOGITS
     necessarily
    1.63
    necessarily
    1.45
     automatically
    1.39
     NECESS
    1.30
     Necess
    1.27
     definitely
    1.27
    definitely
    1.21
     automatiquement
    1.20
     Automatically
    1.19
    Definitely
    1.16
    Activations Density 2.482%

    No Known Activations