© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1463
    Prev
    Next
    INDEX
    Explanations

    various words whose definitions seem positive, important or useful.

    oai_token-act-pair · gemini-2.0-flash

    Non-English text and snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ########.
    -0.87
    出版年
    -0.77
     UIImage
    -0.68
     المعيارى
    -0.68
    Obrázky
    -0.66
    multer
    -0.65
     assumption
    -0.65
     ability
    -0.65
    IntoConstraints
    -0.64
     concept
    -0.64
    POSITIVE LOGITS
     Процитовано
    0.50
     brevemente
    0.48
    ographia
    0.46
    terscotch
    0.46
     CYTHON
    0.46
     McCullough
    0.46
    logías
    0.46
     DOLLARS
    0.45
    ynthetic
    0.44
    tamen
    0.44
    Activations Density 6.139%

    No Known Activations