© 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. 5194
    Prev
    Next
    INDEX
    Explanations

    negative auxiliary verbs "don't", "shouldn't", and "not"

    oai_token-act-pair · gemini-2.0-flash

    technical terms and jargon

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

    Negation

    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
     calendriers
    -0.59
     positive
    -0.51
     Verständnis
    -0.50
    ніципа
    -0.48
    weisen
    -0.48
     rez
    -0.47
    Erreferentziak
    -0.47
    ]!=
    -0.47
     União
    -0.47
    EndContext
    -0.46
    POSITIVE LOGITS
     lenker
    0.62
     مشين
    0.60
    envolvimento
    0.56
     <>",
    0.55
     NLA
    0.52
    LITE
    0.52
    SequentialGroup
    0.51
    Xna
    0.51
    ništ
    0.51
    ScopeManager
    0.50
    Activations Density 0.700%

    No Known Activations