© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4142
    Prev
    Next
    INDEX
    Explanations

    French words and phrases, particularly greetings, goodbyes, and time- or date-related terms.

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act-logits · gemini-2.0-flash

    French

    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_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
     autorytatywna
    -0.73
     médicaux
    -0.73
     démocr
    -0.70
     supérieurs
    -0.67
     urbanas
    -0.67
     téléph
    -0.64
    awtextra
    -0.63
     brancas
    -0.63
     financieros
    -0.63
    SupportActionBar
    -0.63
    POSITIVE LOGITS
    كويكب
    0.52
     незавершена
    0.49
    TypedDataSet
    0.48
     Tyrone
    0.46
     consolid
    0.46
    sendStatus
    0.45
    DeleteBehavior
    0.44
     "..\..\..\
    0.44
     verm
    0.44
     "..\..\
    0.44
    Activations Density 0.809%

    No Known Activations