© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9887
    Prev
    Next
    INDEX
    Explanations

    location names within Poland

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     A
    -0.51
     at
    -0.49
    bori
    -0.47
     
    -0.44
     Type
    -0.44
    reuil
    -0.43
     At
    -0.43
     y
    -0.42
     L
    -0.42
    ját
    -0.41
    POSITIVE LOGITS
    sizeCache
    1.01
     resourceCulture
    0.91
     pinulongan
    0.87
    tvguidetime
    0.85
     يتيمه
    0.84
    Viitteet
    0.83
    WireFormatLite
    0.82
    oredCriteria
    0.82
     OFDb
    0.82
     بيها
    0.81
    Activations Density 0.217%

    No Known Activations