© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9937
    Prev
    Next
    INDEX
    Explanations

    references to research funding, organizations, and people

    oai_token-act-pair · gemini-2.0-flash

    Foundation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    rungsseite
    -0.79
    出版年
    -0.71
     unknownFields
    -0.71
     mxArray
    -0.68
    WindowConstants
    -0.67
     دیکھیے
    -0.66
     nonatomic
    -0.66
    ########.
    -0.65
     Walkover
    -0.65
    ConstraintMaker
    -0.63
    POSITIVE LOGITS
    stellen
    0.47
    PMailer
    0.45
    msgTypes
    0.45
    CRR
    0.45
    PreferredItem
    0.44
     atteinte
    0.44
    BEE
    0.43
    icia
    0.43
     craindre
    0.43
     doc
    0.42
    Activations Density 2.466%

    No Known Activations