© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8004
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States and other places, especially in connection with travel or geography.

    oai_token-act-pair · gemini-2.0-flash

    words related to names and places

    np_token-act-pair-logits · gpt-4o-mini

    Place 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    here
    -0.57
    ↘
    -0.53
     ici
    -0.53
    Here
    -0.53
     aquí
    -0.51
    GEBURTSDATUM
    -0.50
     here
    -0.50
     Here
    -0.49
    //
    -0.49
     tutaj
    -0.48
    POSITIVE LOGITS
     Roskov
    0.81
     esternos
    0.75
    niająca
    0.66
    StoryboardSegue
    0.64
     EconPapers
    0.64
     гля
    0.64
     together
    0.64
    scriptId
    0.62
    AutoScaleMode
    0.59
    "])
    0.59
    Activations Density 8.239%

    No Known Activations