© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6415
    Prev
    Next
    INDEX
    Explanations

    words with German suffixes or related to German language, along with some other seemingly unrelated words

    oai_token-act-pair · gemini-2.0-flash

    German language fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ForValue
    -0.57
    macar
    -0.52
     Infan
    -0.52
     Numerology
    -0.51
    InSection
    -0.51
     Guts
    -0.49
     Paralymp
    -0.49
     sbag
    -0.49
    atch
    -0.47
     taf
    -0.47
    POSITIVE LOGITS
    <bos>
    1.38
    RTEE
    0.68
    izare
    0.65
     efficient
    0.65
    Pyx
    0.64
    PerformLayout
    0.62
    Efficient
    0.62
     Efficient
    0.60
     مصرى
    0.60
    izarea
    0.59
    Activations Density 0.435%

    No Known Activations