© 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. 13577
    Prev
    Next
    INDEX
    Explanations

    dates, laws, and times

    oai_token-act-pair · gemini-2.0-flash

    legal and citations

    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
    ApiController
    -0.55
     approval
    -0.47
    approval
    -0.47
    (!__
    -0.46
    MIA
    -0.46
     Mujer
    -0.45
     fasi
    -0.45
     fédéral
    -0.44
     approves
    -0.44
     Hidup
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.73
     ComVisible
    0.72
    Демографія
    0.67
    VersionUID
    0.65
     createState
    0.62
    withIdentifier
    0.59
     '{@
    0.58
     Bioaccumulative
    0.58
    లాలు
    0.56
    enziali
    0.55
    Activations Density 1.679%

    No Known Activations