© 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. 9632
    Prev
    Next
    INDEX
    Explanations

    years in the 1990s and 2000s

    oai_token-act-pair · gemini-2.0-flash

    9

    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
     Meksiku
    -0.99
     photolibrary
    -0.98
     HasFactory
    -0.96
     doubtnut
    -0.93
     scania
    -0.91
     Anaconda
    -0.87
     piaggio
    -0.82
     hilux
    -0.82
     helico
    -0.81
    TypedDataSet
    -0.81
    POSITIVE LOGITS
     and
    0.92
     or
    0.90
     in
    0.82
     on
    0.72
     which
    0.70
     a
    0.69
     an
    0.68
     as
    0.68
    .
    0.66
    ,
    0.66
    Activations Density 1.794%

    No Known Activations