© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5172
    Prev
    Next
    INDEX
    Explanations

    clauses that contain conjunctions and commas.

    oai_token-act-pair · gemini-2.0-flash

    "however"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Referanser
    -0.97
    LEncoder
    -0.90
     يتيمه
    -0.81
    存于互联网档案馆
    -0.77
    Hentet
    -0.73
     DriverManager
    -0.69
    JNIEnv
    -0.68
     ویکی‌پدیای
    -0.66
    igslist
    -0.65
    terday
    -0.65
    POSITIVE LOGITS
     however
    2.97
    however
    2.50
     entanto
    2.45
     però
    2.36
    However
    2.06
     though
    1.97
     porém
    1.97
     However
    1.96
     tuttavia
    1.90
     cependant
    1.84
    Activations Density 0.191%

    No Known Activations