© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15487
    Prev
    Next
    INDEX
    Explanations

    multiple strings in what looks like different languages related to shop functions and also C++ typename definitions and also words related to assumptions

    oai_token-act-pair · gemini-2.0-flash

    mixed languages and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ведення
    -1.14
     волосся
    -1.11
     дії
    -1.09
     якого
    -1.09
     вік
    -1.09
     застосування
    -1.06
     кіль
    -1.04
     виправи
    -1.00
     собі
    -1.00
     немає
    -0.98
    POSITIVE LOGITS
     виправивши
    1.10
    amaño
    1.07
     Organis
    1.04
    Organis
    1.03
     moulds
    1.02
     Organisations
    1.00
     Organiser
    0.98
     незавершена
    0.98
     ſont
    0.98
     ainfi
    0.97
    Activations Density 0.843%

    No Known Activations