© 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. 9915
    Prev
    Next
    INDEX
    Explanations

    the word "deck."

    oai_token-act-pair · gemini-2.0-flash

    deck

    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
     for
    -0.69
     concerns
    -0.57
    on
    -0.53
    อบ
    -0.51
     favorite
    -0.51
    сло
    -0.51
    te
    -0.51
     favorites
    -0.49
     of
    -0.49
    po
    -0.49
    POSITIVE LOGITS
     Мексичка
    1.20
     >=",
    1.20
    LookAnd
    1.17
    EDEFAULT
    1.05
    !*\
    1.02
    uxxxx
    1.02
    tagHelperRunner
    1.01
    sizeCache
    0.98
    LEncoder
    0.98
    aarrggbb
    0.97
    Activations Density 0.498%

    No Known Activations