© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14532
    Prev
    Next
    INDEX
    Explanations

    LaTeX or other math style equations or formula formatting markups.

    oai_token-act-pair · gemini-2.0-flash

    aligned

    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
    ########.
    -0.63
    EndGlobalSection
    -0.55
    InitVars
    -0.55
     HasFactory
    -0.52
     "¿
    -0.51
     않
    -0.50
     écl
    -0.50
     Hurt
    -0.50
     mendes
    -0.50
    धिक
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    webElementXpaths
    0.61
     gawas
    0.59
     مرئيه
    0.57
     isNameExpr
    0.57
     propOrder
    0.55
    __':
    0.55
    Hentet
    0.54
    出版年
    0.54
    Ễ
    0.54
    Activations Density 3.198%

    No Known Activations