© 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. 13618
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate positive sentiment towards locations, paths, and trails.

    oai_token-act-pair · gemini-2.0-flash

    locations and experiences

    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
    fone
    -0.48
    element
    -0.47
    uri
    -0.46
     powiet
    -0.45
     Ostro
    -0.45
    gn
    -0.43
    re
    -0.43
    ্দ
    -0.43
     Dés
    -0.42
    lig
    -0.42
    POSITIVE LOGITS
     المعيارى
    0.77
    engertian
    0.69
     دیکھیے
    0.67
    ✨:
    0.66
     يتيمه
    0.65
    \{\\
    0.65
     autorytatywna
    0.65
     الرياضيه
    0.63
    NOPQRST
    0.62
    SizeMode
    0.61
    Activations Density 0.061%

    No Known Activations