© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12429
    Prev
    Next
    INDEX
    Explanations

    the phrase "as well"

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating "well" or positive conditions

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

    "as well"

    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
     plus
    -0.83
     +
    -0.63
     along
    -0.60
     u
    -0.59
     OR
    -0.57
     PLUS
    -0.56
     junto
    -0.56
    plus
    -0.56
     Plus
    -0.54
     Along
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.98
     initComponents
    0.96
    NUMX
    0.95
    出版年
    0.92
     contextLoads
    0.89
    IntoConstraints
    0.88
     NSCoder
    0.87
    __*/
    0.87
     raiſ
    0.82
     myſelf
    0.82
    Activations Density 1.517%

    No Known Activations