© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15867
    Prev
    Next
    INDEX
    Explanations

    the German word "so" preceded by words related to quiet or space

    oai_token-act-pair · gemini-2.0-flash

    German language

    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
     a
    -0.72
    XmlAccessType
    -0.47
    臨
    -0.46
     للاسماء
    -0.44
    onz
    -0.42
    ltä
    -0.42
    ئ
    -0.41
     Richter
    -0.40
     HasFactory
    -0.40
    ッソ
    -0.40
    POSITIVE LOGITS
     EconPapers
    0.68
    Autoritní
    0.68
     AssemblyCulture
    0.63
    Personendaten
    0.63
     Jefus
    0.62
     PLWABN
    0.62
     Efq
    0.61
     jScrollPane
    0.60
    $_['
    0.60
    webElementXpaths
    0.60
    Activations Density 0.284%

    No Known Activations