© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8368
    Prev
    Next
    INDEX
    Explanations

    references to time periods

    oai_token-act-pair · gemini-2.0-flash

    Time, reflections, and impressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     and
    -0.75
    ,
    -0.71
     (
    -0.67
     in
    -0.64
     or
    -0.52
    ;
    -0.50
     is
    -0.50
     that
    -0.50
     of
    -0.50
     for
    -0.48
    POSITIVE LOGITS
     Efq
    1.41
    SharedDtor
    1.23
    PreferredItem
    1.23
     purpoſe
    1.18
     Jefus
    1.18
    MigrationBuilder
    1.16
    awtextra
    1.16
    DeleteBehavior
    1.16
     myſelf
    1.15
     Theſe
    1.13
    Activations Density 3.464%

    No Known Activations