© 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. 4627
    Prev
    Next
    INDEX
    Explanations

    uses cases of 'but' and related words used to contrast 2 things

    oai_token-act-pair · gemini-2.0-flash

    words or phrases indicating contrast or exceptions

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

    options and alternatives

    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
     مشين
    -1.13
     незавершена
    -1.10
    +#+#
    -1.02
    principalColumn
    -0.98
    Дереккөздер
    -0.96
    expandindo
    -0.94
     beginnetje
    -0.94
     Numerade
    -0.90
     विश्वसनीयता
    -0.89
     الحره
    -0.89
    POSITIVE LOGITS
    amer
    0.46
     to
    0.42
    lö
    0.42
    ü
    0.41
    HttpHeaders
    0.40
     ImageIcon
    0.40
     aside
    0.40
    Ren
    0.39
     Rade
    0.39
    راق
    0.38
    Activations Density 6.899%

    No Known Activations