© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13076
    Prev
    Next
    INDEX
    Explanations

    the word "sim" and variations thereof, possibly in the context of computer simulations

    oai_token-act-pair · gemini-2.0-flash

    Sim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     sim
    -2.42
    Sim
    -2.30
    sim
    -2.23
     Sim
    -2.19
    SIM
    -1.97
     SIM
    -1.81
     sims
    -1.39
    sims
    -1.34
     simulation
    -1.23
     Simulation
    -1.19
    POSITIVE LOGITS
    expandindo
    0.92
     مشين
    0.86
    tvguidetime
    0.82
     MainAxisSize
    0.78
     للاسماء
    0.78
    ValueStyle
    0.74
    DotNetBar
    0.74
     onOptions
    0.72
    клопе
    0.72
    Clik
    0.68
    Activations Density 1.578%

    No Known Activations