© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4949
    Prev
    Next
    INDEX
    Explanations

    the word "subject" or "subjects"

    oai_token-act-pair · gemini-2.0-flash

    subject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     subject
    -0.93
    subject
    -0.73
     Subject
    -0.61
     in
    -0.54
    фициальный
    -0.53
     
    -0.52
    Subject
    -0.51
    </em>
    -0.51
     sujets
    -0.50
     subjects
    -0.50
    POSITIVE LOGITS
     &___
    1.05
     CreateTagHelper
    1.03
    yntaxException
    1.02
    tvguidetime
    1.01
     MonoBehaviour
    1.01
    bootstrapcdn
    1.00
     initComponents
    0.97
     <>",
    0.97
    __':
    0.96
     HasFactory
    0.96
    Activations Density 1.638%

    No Known Activations