© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15627
    Prev
    Next
    INDEX
    Explanations

    the word "the" alone or grouped with other words, or words referring to structures or historical sites.

    oai_token-act-pair · gemini-2.0-flash

    the/s

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    GEBURTSDATUM
    -0.82
     resourceCulture
    -0.72
    Lähteet
    -0.69
     Wikiseite
    -0.69
    InjectAttribute
    -0.67
     découver
    -0.66
     ainfi
    -0.66
    migrationBuilder
    -0.63
     parteci
    -0.63
     feroit
    -0.62
    POSITIVE LOGITS
     inim
    0.60
     indol
    0.60
     shivering
    0.59
     efferves
    0.57
     stuttering
    0.56
     diminutive
    0.56
     feverish
    0.56
     blushing
    0.55
     shadowy
    0.53
     angelic
    0.53
    Activations Density 3.076%

    No Known Activations