© 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. 12037
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate that the speaker is about to make an important qualification or nuance of something

    oai_token-act-pair · gemini-2.0-flash

    sequences indicating uncertainty or implications

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

    Especially/Particularly

    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
    Datuak
    -0.63
    шь
    -0.52
     gärna
    -0.51
    bodyParser
    -0.50
     Those
    -0.49
     Both
    -0.48
    Both
    -0.48
    Those
    -0.47
     insbesondere
    -0.45
     především
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.73
    IntoConstraints
    0.69
    WireFormatLite
    0.66
     when
    0.65
    tvguidetime
    0.62
    出版年
    0.62
     المعيارى
    0.61
     poffible
    0.60
    ronpa
    0.59
    Obrázky
    0.58
    Activations Density 17.667%

    No Known Activations