© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6481
    Prev
    Next
    INDEX
    Explanations

    mentions of grammatical tense and simple declarative clauses

    oai_token-act-pair · gemini-2.0-flash

    verb tense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Мексичка
    -0.57
    SourceChecksum
    -0.57
    AccessorTable
    -0.55
    NavController
    -0.54
    octanol
    -0.52
     okuyayım
    -0.51
     Sécurité
    -0.49
    Geographie
    -0.49
    انيف
    -0.48
    lunda
    -0.48
    POSITIVE LOGITS
     past
    1.22
    Past
    1.06
     tense
    1.05
    past
    1.03
     Past
    1.03
     Tense
    0.90
     PAST
    0.87
     present
    0.85
     verb
    0.82
     Present
    0.82
    Activations Density 0.369%

    No Known Activations