© 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. 9808
    Prev
    Next
    INDEX
    Explanations

    seemingly random words from different European languages, possibly named entities

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    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
    GraphicsUnit
    -0.91
    WithIOException
    -0.75
    MLLoader
    -0.72
    XmlEnum
    -0.71
     ApiException
    -0.70
     BoxFit
    -0.68
    AndEndTag
    -0.67
    queryInterface
    -0.66
    @[+][
    -0.65
    Gön
    -0.64
    POSITIVE LOGITS
     >=",
    0.49
     stá
    0.46
    ES
    0.43
    pote
    0.43
     luce
    0.42
    öre
    0.42
     Heeren
    0.42
    este
    0.41
    ное
    0.41
    RatingBar
    0.41
    Activations Density 0.419%

    No Known Activations