© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10437
    Prev
    Next
    INDEX
    Explanations

    the word "seed", sometimes followed or preceded in the sentence by other agricultural terms, measurements, or the description of a process

    oai_token-act-pair · gemini-2.0-flash

    seeds

    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
     Monfieur
    -1.06
     Jefus
    -0.96
     purpoſe
    -0.93
     houſe
    -0.92
     Cæsar
    -0.91
     Houſe
    -0.91
     bénéfices
    -0.88
     fumée
    -0.85
     Reſ
    -0.84
     själva
    -0.83
    POSITIVE LOGITS
     dis
    0.63
     total
    0.60
     dispar
    0.57
     relevant
    0.55
    cipline
    0.54
    campista
    0.54
     somme
    0.52
     Seeder
    0.52
    posia
    0.51
     most
    0.51
    Activations Density 1.660%

    No Known Activations