© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16310
    Prev
    Next
    INDEX
    Explanations

    nonsensical text about fighting, power, and a world called "Dan"

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    PRNewswire
    -0.66
    IndentedString
    -0.59
    ThroughAttribute
    -0.58
    protoimpl
    -0.58
    endregion
    -0.58
     transfieras
    -0.57
     BrowserModule
    -0.55
     Bioaccumulative
    -0.55
    abestanden
    -0.52
    BrowserRouter
    -0.50
    POSITIVE LOGITS
     Signalez
    0.53
     uska
    0.51
    $_['
    0.49
    venez
    0.48
    Datuak
    0.47
    כום
    0.46
     işle
    0.46
    nél
    0.45
    Jvm
    0.44
    rdag
    0.43
    Activations Density 3.282%

    No Known Activations