© 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. 12741
    Prev
    Next
    INDEX
    Explanations

    code snippets and code-related terms in different programming languages

    oai_token-act-pair · gemini-2.0-flash

    Code and mixed languages

    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
     cérami
    -1.42
     varandra
    -1.38
     démocr
    -1.35
     jouets
    -1.32
     fermés
    -1.30
     automatiques
    -1.26
     garanzia
    -1.24
     stället
    -1.22
     fumée
    -1.22
     énergé
    -1.21
    POSITIVE LOGITS
     PERT
    0.40
     agr
    0.40
     noirs
    0.40
     Suma
    0.39
     verkle
    0.39
     Tierra
    0.38
    aggia
    0.38
    ggers
    0.38
    ensas
    0.38
    idet
    0.37
    Activations Density 0.324%

    No Known Activations