© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12049
    Prev
    Next
    INDEX
    Explanations

    dates, times, and references to historical events.

    oai_token-act-pair · gemini-2.0-flash

    Categories or types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Vidite
    -0.62
    Portale
    -0.60
     gepubliceerd
    -0.54
     jährlich
    -0.54
     damals
    -0.53
    当時は
    -0.52
     pernah
    -0.52
    Personensuche
    -0.50
     beginnetje
    -0.49
     annually
    -0.49
    POSITIVE LOGITS
    ंदीखरीदारी
    0.61
    /*
    0.55
    servable
    0.54
    istoitu
    0.53
    RenderAtEndOf
    0.52
     MainAxisSize
    0.51
    ględ
    0.50
    vestream
    0.49
    ütfen
    0.49
     COVID
    0.48
    Activations Density 3.957%

    No Known Activations