© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9278
    Prev
    Next
    INDEX
    Explanations

    words related to organizations and collaborative efforts

    oai_token-act-pair · gemini-2.0-flash

    program implementation

    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
    Negative Logits
    UnknownFields
    -0.66
     EconPapers
    -0.62
     Diakses
    -0.61
    RenderAtEndOf
    -0.56
     ©️
    -0.54
    RTEE
    -0.52
    ContentAsync
    -0.50
     psu
    -0.49
     bpy
    -0.49
    isième
    -0.48
    POSITIVE LOGITS
    ArgsConstructor
    0.65
     ProtoMessage
    0.61
     consultato
    0.55
     متعلقه
    0.54
     peindre
    0.54
     svol
    0.53
     herum
    0.53
     mourir
    0.53
     craindre
    0.53
     morire
    0.52
    Activations Density 1.847%

    No Known Activations