© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10645
    Prev
    Next
    INDEX
    Explanations

    mentions of Spanish places and soccer teams

    oai_token-act-pair · gemini-2.0-flash

    Spanish locations/names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     think
    -1.16
     Think
    -1.01
    Think
    -0.98
    think
    -0.85
     THINK
    -0.76
     thinks
    -0.71
    THINK
    -0.62
     denk
    -0.52
     pense
    -0.51
    UserScript
    -0.50
    POSITIVE LOGITS
    RectangleBorder
    0.71
    entary
    0.56
     máu
    0.54
     Cultures
    0.54
    ContentAsync
    0.54
    watches
    0.52
    ])):
    0.52
     BorderRadius
    0.52
    Filmografie
    0.51
    ThroughAttribute
    0.51
    Activations Density 0.388%

    No Known Activations