© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12652
    Prev
    Next
    INDEX
    Explanations

    text from online game comments, specifically relating to gameplay actions

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     <<<<<<<<<<<<<<
    -0.77
    )++;
    -0.74
     $_"
    -0.70
    ]++;
    -0.63
     GIPHY
    -0.63
     Audiodateien
    -0.62
     BIBSYS
    -0.62
     églises
    -0.62
    Xna
    -0.61
     čierna
    -0.60
    POSITIVE LOGITS
    ionario
    0.44
    RunAsync
    0.38
     kasarigan
    0.37
    LayoutManager
    0.37
     MERCHANTABILITY
    0.37
     AssemblyCulture
    0.36
    lodge
    0.36
    abetes
    0.36
     aven
    0.36
    cloak
    0.36
    Activations Density 4.839%

    No Known Activations