© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2741
    Prev
    Next
    INDEX
    Explanations

    words implying hidden location and treasure

    oai_token-act-pair · gemini-2.0-flash

    hidden, lurking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    TagMode
    -0.68
    MigrationBuilder
    -0.68
    DeleteBehavior
    -0.57
    Билгалдахарш
    -0.57
    httphttps
    -0.57
     Extragalactic
    -0.57
     Италијани
    -0.56
    RenderAtEndOf
    -0.56
    IUrlHelper
    -0.56
    évaluateur
    -0.55
    POSITIVE LOGITS
     hidden
    1.42
     hiding
    1.41
     lurking
    1.22
    hidden
    1.21
    hiding
    1.16
     Hiding
    1.16
    Hidden
    1.15
     Hidden
    1.12
     concealed
    1.12
     скры
    1.10
    Activations Density 1.981%

    No Known Activations