© 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. 12387
    Prev
    Next
    INDEX
    Explanations

    words and phrases in foreign languages like French and Italian.

    oai_token-act-pair · gemini-2.0-flash

    Foreign language snippets

    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
    Personensuche
    -1.42
     للاسماء
    -1.39
     nakalista
    -1.39
    AndEndTag
    -1.38
     estekak
    -1.38
    RenderAtEndOf
    -1.36
     виправивши
    -1.32
    LookAnd
    -1.32
    OGND
    -1.29
     '\\;'
    -1.27
    POSITIVE LOGITS
     quæ
    0.17
     Monfieur
    0.14
     Majefty
    0.10
     Jefus
    0.09
     enfans
    0.08
     iſt
    0.07
     fumée
    0.06
    ſelves
    0.05
    ſelf
    0.05
     avoient
    0.05
    Activations Density 1.480%

    No Known Activations