© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13508
    Prev
    Next
    INDEX
    Explanations

    mentions of a person (often indicated by pronoun use), with activation increasing if the person is doing something, had something done to them, or is in a state of being.

    oai_token-act-pair · gemini-2.0-flash

    biographies

    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
    Geplaatst
    -0.61
    IsContent
    -0.56
    Viitteet
    -0.55
     intptr
    -0.54
    AndroidJUnit
    -0.53
     referenties
    -0.53
    MessageOf
    -0.51
    脚注の使い方
    -0.51
     OFDb
    -0.50
     pinulongan
    -0.50
    POSITIVE LOGITS
    limus
    0.53
    urangi
    0.52
    usda
    0.49
    catat
    0.47
     retained
    0.47
    xpress
    0.46
    ляю
    0.46
    ++]=
    0.46
    +#+
    0.45
     Kasih
    0.45
    Activations Density 0.550%

    No Known Activations