© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4642
    Prev
    Next
    INDEX
    Explanations

    text in French in an internet chat context, possibly discussing servers

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash

    French words Method used: 1 — because top tokens are French; French words

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     et
    -0.57
    inė
    -0.56
     alfo
    -0.54
     gương
    -0.51
     Dat
    -0.51
     Brun
    -0.51
    isas
    -0.50
    wixt
    -0.50
    ="#"><
    -0.49
     Fet
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.81
    enumi
    0.80
    withIdentifier
    0.78
    دانشنامهٔ
    0.72
     فريبيس
    0.70
    HasForeignKey
    0.69
     виправивши
    0.69
     محفوظة
    0.69
     propOrder
    0.69
     насељу
    0.68
    Activations Density 0.381%

    No Known Activations