© 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. 1785
    Prev
    Next
    INDEX
    Explanations

    sentences that contain references to actions or views of people

    oai_token-act-pair · 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
     mourut
    -0.71
     humanidade
    -0.60
     humaines
    -0.58
    SharedDtor
    -0.56
     religieuses
    -0.55
     étoient
    -0.55
     fotográfico
    -0.54
     étoit
    -0.54
     électroniques
    -0.52
     itſelf
    -0.52
    POSITIVE LOGITS
     يتيمه
    0.69
    cèse
    0.65
    InjectAttribute
    0.63
    RenderAtEndOf
    0.63
    idjan
    0.61
     Exactos
    0.60
     doing
    0.60
     kasarigan
    0.60
     taking
    0.60
    \{\\
    0.59
    Activations Density 3.238%

    No Known Activations