© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14125
    Prev
    Next
    INDEX
    Explanations

    It finds common words in French, especially in lyrics or quotations

    oai_token-act-pair · gemini-2.0-flash

    Multiple languages

    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
    JNIEnv
    -0.52
    kloped
    -0.44
    HtmlAttribute
    -0.39
     Khat
    -0.38
    StackNavigator
    -0.38
     Kej
    -0.37
    kheim
    -0.37
    idjan
    -0.36
    ollectionView
    -0.35
    ocell
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.50
     luxo
    0.47
    ียว
    0.47
     perna
    0.47
     ense
    0.47
     saine
    0.46
    הערות
    0.46
     gà
    0.46
     barca
    0.46
    ↘
    0.46
    Activations Density 11.270%

    No Known Activations