© 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. 11655
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death, violence, harm, and destruction.

    oai_token-act-pair · gemini-2.0-flash

    death

    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
    principalColumn
    -0.75
    ########.
    -0.69
    TagMode
    -0.63
    GeoNames
    -0.61
    RenderAtEndOf
    -0.59
    HasIndex
    -0.59
    \}_{
    -0.59
    '][]
    -0.58
    jooq
    -0.57
     kasarigan
    -0.57
    POSITIVE LOGITS
     edited
    0.50
     edit
    0.47
     <<<<<<<<<<<<<<
    0.46
    それぞれ
    0.44
    Рис
    0.43
     irgendwo
    0.43
    Edited
    0.42
    mes
    0.42
    yard
    0.42
    หมือน
    0.42
    Activations Density 1.959%

    No Known Activations