© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5435
    Prev
    Next
    INDEX
    Explanations

    the german words "musik" and "stykker"

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Външни
    -0.75
    +#+#
    -0.72
    +#+
    -0.71
    AÇÃO
    -0.66
     Wikispecies
    -0.66
    ########.
    -0.65
    esserts
    -0.63
    calcium
    -0.62
     Waray
    -0.61
     propOrder
    -0.61
    POSITIVE LOGITS
     crí
    0.51
    振
    0.48
    nav
    0.48
    h
    0.47
    牢
    0.46
     noqa
    0.45
    ont
    0.44
    p
    0.44
    sh
    0.44
    op
    0.43
    Activations Density 0.740%

    No Known Activations