© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1896
    Prev
    Next
    INDEX
    Explanations

    language associated with royalty, nobility, and high-fantasy world-building

    oai_token-act-pair · gemini-2.0-flash

    Royal/formal language

    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
     NASA
    -0.56
     garcía
    -0.54
     Battista
    -0.53
     Dickerson
    -0.52
    junta
    -0.52
     Silverman
    -0.52
     Sousa
    -0.52
     clinica
    -0.52
     Monteiro
    -0.52
    mafia
    -0.51
    POSITIVE LOGITS
     дописавши
    0.53
     autorytatywna
    0.52
     <<<<<<<<<<<<<<
    0.51
    raff
    0.51
     defaultstate
    0.49
     Ys
    0.49
    дарь
    0.48
     thorn
    0.47
     kins
    0.46
    writeField
    0.45
    Activations Density 49.621%

    No Known Activations