© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3440
    Prev
    Next
    INDEX
    Explanations

    French words and sentence fragments

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash

    French le/l'

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     la
    -0.95
    La
    -0.68
     La
    -0.58
    la
    -0.58
    Το
    -0.57
     le
    -0.48
     il
    -0.47
    P
    -0.46
    Le
    -0.45
    A
    -0.45
    POSITIVE LOGITS
     Anſ
    0.79
     **/
    0.77
    NUMX
    0.77
    AccessorTable
    0.75
     Majefty
    0.75
    Бахар
    0.73
     ſeveral
    0.73
    NameInMap
    0.73
    tagHelperRunner
    0.72
    sitive
    0.72
    Activations Density 11.567%

    No Known Activations