© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 441
    Prev
    Next
    INDEX
    Explanations

    code snippets from multiple languages including German, French and English.

    oai_token-act-pair · gemini-2.0-flash

    French (and German) text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SourceChecksum
    -0.68
     виправивши
    -0.63
     noDo
    -0.60
     spørs
    -0.59
     שוליים
    -0.57
     spørsmål
    -0.56
    OGND
    -0.55
    Jîn
    -0.55
    Personensuche
    -0.54
    enseignements
    -0.54
    POSITIVE LOGITS
     publice
    0.50
     vario
    0.47
     ་་
    0.46
    Formazione
    0.43
     infinito
    0.42
     Macle
    0.41
    tifies
    0.41
     itſelf
    0.41
     dise
    0.40
     Theſe
    0.40
    Activations Density 0.623%

    No Known Activations