© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14859
    Prev
    Next
    INDEX
    Explanations

    words related to religious ceremonies or proclamations

    oai_token-act-pair · gemini-2.0-flash

    Announcing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.77
    Hozzáférés
    -0.66
    databind
    -0.64
     toJson
    -0.57
    日閲覧
    -0.57
    цездатний
    -0.56
     Bourgoin
    -0.56
    henge
    -0.54
    akukan
    -0.54
    ($__
    -0.53
    POSITIVE LOGITS
     ivelany
    0.57
     Continuous
    0.55
    Voci
    0.54
    ReusableCell
    0.54
     annonce
    0.54
    protoc
    0.53
    ArrowToggle
    0.53
     proclaim
    0.51
     pubb
    0.50
     proclaimed
    0.50
    Activations Density 1.746%

    No Known Activations