© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13745
    Prev
    Next
    INDEX
    Explanations

    terms related to cryptocurrency

    oai_token-act-pair · gemini-2.0-flash

    bitcoin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     sindic
    -0.58
    ztály
    -0.56
     cordes
    -0.55
     betweenstory
    -0.55
     ouvriers
    -0.54
     reisen
    -0.53
     demas
    -0.53
     ſmall
    -0.52
     perſon
    -0.52
     CURLOPT
    -0.50
    POSITIVE LOGITS
    wapV
    0.63
     useAppContext
    0.60
    JpaRepository
    0.59
     Roskov
    0.59
     nahilalakip
    0.57
    VolleyError
    0.57
    openzeppelin
    0.57
    IContainer
    0.55
    Билгалдахарш
    0.53
    setVerticalGroup
    0.52
    Activations Density 0.242%

    No Known Activations