© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4357
    Prev
    Next
    INDEX
    Explanations

    the word "path" and sometimes words associated with religion or time

    oai_token-act-pair · gemini-2.0-flash

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     مشتر
    -0.70
     لط
    -0.70
     Perſ
    -0.69
     Tecn
    -0.68
     coverage
    -0.63
     firsthand
    -0.63
     Conſ
    -0.62
     Verſ
    -0.61
    weren
    -0.61
     verdi
    -0.61
    POSITIVE LOGITS
    ttino
    0.75
    brigens
    0.73
     actionMode
    0.69
    tanleria
    0.67
     ISNI
    0.67
    cillor
    0.66
    reszcie
    0.66
     Himo
    0.65
     "..\..\..\
    0.65
     متحده
    0.65
    Activations Density 0.969%

    No Known Activations