© 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. 10197
    Prev
    Next
    INDEX
    Explanations

    locations, especially in Manhattan

    oai_token-act-pair · gemini-2.0-flash

    geographical references or locations

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

    New York 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
    DialogContent
    -0.48
    jatel
    -0.46
    Reactivity
    -0.45
     quibus
    -0.44
     انتظار
    -0.43
    تهى
    -0.42
    amethasone
    -0.41
     zakład
    -0.41
    heça
    -0.41
     recommandons
    -0.40
    POSITIVE LOGITS
    IsMutable
    0.86
     كومونز
    0.77
     Meksiku
    0.75
     للاسماء
    0.75
    ValueStyle
    0.73
    GraphicsUnit
    0.70
    出版年
    0.69
     للمعارف
    0.69
     Chwiliwch
    0.69
     الاطلاع
    0.69
    Activations Density 1.160%

    No Known Activations