© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10389
    Prev
    Next
    INDEX
    Explanations

    words that end in "ed" or "ing", are prefixes, or have other suffixes attached.

    oai_token-act-pair · gemini-2.0-flash

    nef

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    '
    -0.48
     
    -0.43
    ↵↵
    -0.39
    ↵
    -0.39
      
    -0.38
     and
    -0.38
     the
    -0.37
     for
    -0.36
    ’
    -0.35
     or
    -0.35
    POSITIVE LOGITS
     defaultstate
    1.00
    setVerticalGroup
    0.99
    DockStyle
    0.93
    Tembelea
    0.90
    styleType
    0.88
    TintMode
    0.88
     himo
    0.88
    تقاوى
    0.88
    tvguidetime
    0.87
     disambiguazione
    0.86
    Activations Density 1.262%

    No Known Activations