© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5269
    Prev
    Next
    INDEX
    Explanations

    a mix of Spanish and French articles ("la", "una") and possessive adjectives ("sa", "propre") within a larger context of mixed-language text.

    oai_token-act-pair · gemini-2.0-flash

    la

    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
    .*")]
    -0.61
    Gön
    -0.56
     onCreateView
    -0.56
     createState
    -0.53
    hasMoreElements
    -0.52
     transfieras
    -0.51
    reiter
    -0.50
    ührung
    -0.48
     initComponents
    -0.48
    entrySet
    -0.48
    POSITIVE LOGITS
    kháu
    0.47
     linkovi
    0.46
    bores
    0.46
    strar
    0.45
    ContentAsync
    0.44
    Filmografie
    0.44
    قایناقلار
    0.44
    sonian
    0.44
     APT
    0.44
     DCC
    0.43
    Activations Density 0.322%

    No Known Activations