© 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. 1120
    Prev
    Next
    INDEX
    Explanations

    words from languages other than English related to deity

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
    chans
    -0.52
    entz
    -0.50
    hahn
    -0.49
     Stock
    -0.48
    illotine
    -0.47
    KEE
    -0.47
    σχ
    -0.47
    muz
    -0.46
    новништво
    -0.46
    Stock
    -0.46
    POSITIVE LOGITS
     Roskov
    0.90
     utafitiHapana
    0.83
    Personendaten
    0.74
    MigrationBuilder
    0.69
    buttonBar
    0.66
    StoryboardSegue
    0.63
     kaarangay
    0.59
    InstanceState
    0.58
    __':
    0.58
    исленность
    0.58
    Activations Density 0.386%

    No Known Activations