© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15716
    Prev
    Next
    INDEX
    Explanations

    the word "OK", and also the word "late" when it describes a period of time

    oai_token-act-pair · gemini-2.0-flash

    OK

    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
     ModelExpression
    -1.52
    MigrationBuilder
    -1.44
    ValueStyle
    -1.39
    RenderAtEndOf
    -1.38
    GEBURTSDATUM
    -1.32
    脚注の使い方
    -1.30
    parsedMessage
    -1.29
     kasarigan
    -1.28
    rungsseite
    -1.27
    aarrggbb
    -1.25
    POSITIVE LOGITS
    s
    0.55
     our
    0.54
    nya
    0.51
     the
    0.50
     an
    0.50
    ly
    0.48
     The
    0.47
     for
    0.46
    tention
    0.46
     
    0.45
    Activations Density 1.148%

    No Known Activations