© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16143
    Prev
    Next
    INDEX
    Explanations

    the names of places, people, and organizations, often in a foreign/Latin language

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     sở
    -0.52
     Cal
    -0.51
     continúas
    -0.51
    omencl
    -0.48
     Cu
    -0.46
     갈
    -0.46
     de
    -0.45
     Rep
    -0.44
     pe
    -0.44
     rep
    -0.44
    POSITIVE LOGITS
     ―――――
    0.82
    rrggbb
    0.77
     ragaz
    0.76
     Oggi
    0.74
     Corsica
    0.74
    makeConstraints
    0.74
     Altri
    0.73
    pendientes
    0.73
     noastre
    0.73
     CHAPITRE
    0.73
    Activations Density 2.078%

    No Known Activations