© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10443
    Prev
    Next
    INDEX
    Explanations

    the word "very" and words that modify other words.

    oai_token-act-pair · gemini-2.0-flash

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Very
    -0.78
     very
    -0.73
    Very
    -0.66
    NewRow
    -0.56
    cyklopedia
    -0.55
    بوابة
    -0.54
     très
    -0.52
     VERY
    -0.51
    therin
    -0.50
    very
    -0.50
    POSITIVE LOGITS
     HasFactory
    0.72
    GEBURTSDATUM
    0.69
     auroit
    0.66
    <bos>
    0.66
     feroit
    0.64
    AndEndTag
    0.63
     leſs
    0.62
     étoit
    0.61
    ſelf
    0.60
     pouvoit
    0.60
    Activations Density 0.142%

    No Known Activations