© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14317
    Prev
    Next
    INDEX
    Explanations

    descriptions of the abilities of characters or items in a fantasy setting

    oai_token-act-pair · gemini-2.0-flash

    superpowers

    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
    ReusableCell
    -0.61
    windowFixed
    -0.61
     chi̍t
    -0.60
     ddelweddau
    -0.57
    IsContent
    -0.56
     florales
    -0.55
    AutoField
    -0.52
    +#+
    -0.51
     utafitiHapana
    -0.50
    photobucket
    -0.49
    POSITIVE LOGITS
     ujednoznacz
    0.60
    doGet
    0.56
    onViewCreated
    0.55
    szön
    0.51
     fragmentary
    0.50
    ThreadPool
    0.49
     }{@
    0.49
     durée
    0.48
     Subtraction
    0.48
     empirically
    0.48
    Activations Density 3.857%

    No Known Activations