© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10336
    Prev
    Next
    INDEX
    Explanations

    mentions of place names, particularly cities and geographical locations.

    oai_token-act-pair · gemini-2.0-flash

    words related to cities

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

    city

    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
    要知道
    -0.46
    җ
    -0.46
    das
    -0.45
     das
    -0.45
     De
    -0.45
     cooperative
    -0.44
     par
    -0.44
    वार
    -0.43
    áln
    -0.43
    cale
    -0.43
    POSITIVE LOGITS
     ―――――
    0.68
     city
    0.67
     Theſe
    0.66
     cities
    0.66
    exitRule
    0.65
     виправивши
    0.65
    MigrationBuilder
    0.64
     getCity
    0.64
    Filmografie
    0.63
     ciudadana
    0.62
    Activations Density 0.994%

    No Known Activations