© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9353
    Prev
    Next
    INDEX
    Explanations

    dates and words associated with key life events like birth, marriage, and death

    oai_token-act-pair · gemini-2.0-flash

    died

    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
     يتيمه
    -0.81
    rungsseite
    -0.73
    featureID
    -0.69
    FailureListener
    -0.58
    Autoritní
    -0.58
    Personendaten
    -0.57
    principalTable
    -0.55
    帖最后由
    -0.54
    Démographie
    -0.54
     Bohr
    -0.52
    POSITIVE LOGITS
    EndContext
    0.60
    хьтан
    0.56
     exception
    0.54
     quarante
    0.49
    AddHtmlAttribute
    0.48
    hdashline
    0.47
     Vergnügen
    0.46
     Offisielt
    0.45
    OpenHelper
    0.45
     exce
    0.43
    Activations Density 1.152%

    No Known Activations