© 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. 10781
    Prev
    Next
    INDEX
    Explanations

    code-mixed French and English text from a chat setting, as well as general chatty/conversational words.

    oai_token-act-pair · gemini-2.0-flash

    French computer discussions

    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
     &___
    -0.56
     acolo
    -0.50
    vfill
    -0.49
     tetto
    -0.48
     TDA
    -0.48
    NotFoundError
    -0.48
     kê
    -0.47
     tenuta
    -0.46
     senere
    -0.46
     avesse
    -0.46
    POSITIVE LOGITS
    uxxxx
    0.62
    MessageTagHelper
    0.60
    tagHelperRunner
    0.60
    fromCharCode
    0.56
    ArgumentParser
    0.55
     kasarigan
    0.53
    randomUUID
    0.50
    setVerticalGroup
    0.50
     ivelany
    0.49
    ManagedBean
    0.49
    Activations Density 0.530%

    No Known Activations