© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14219
    Prev
    Next
    INDEX
    Explanations

    words related to a Slavic language, possibly Croatian

    oai_token-act-pair · gemini-2.0-flash

    Czech 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     InputDecoration
    -0.68
    HandlerContext
    -0.59
     for
    -0.58
    原始内容存档于
    -0.57
    Становништво
    -0.56
    UseVisualStyle
    -0.54
     and
    -0.53
     achtergrond
    -0.52
    WireFormatLite
    -0.51
    PRNewswire
    -0.51
    POSITIVE LOGITS
     kteří
    0.66
     která
    0.63
     kterou
    0.62
     jsme
    0.59
     tedy
    0.59
    ENSIS
    0.58
    ETIES
    0.56
     lze
    0.56
    cím
    0.56
     jde
    0.56
    Activations Density 3.818%

    No Known Activations