© 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. 12016
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially Java code

    oai_token-act-pair · gemini-2.0-flash

    brackets/colons

    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
    ⓧ
    -0.75
    IntoConstraints
    -0.65
     typelib
    -0.58
     Dostupné
    -0.57
    SharedCtor
    -0.57
    /**
    -0.57
    例文帳に追加
    -0.56
    الإنجليزية
    -0.55
    \{\\
    -0.54
    AddHtmlAttribute
    -0.54
    POSITIVE LOGITS
     diadakan
    0.54
    safety
    0.53
    shooting
    0.51
     gouvernements
    0.50
     aéri
    0.49
     println
    0.49
    running
    0.49
    probe
    0.49
    simd
    0.49
    benefits
    0.49
    Activations Density 7.987%

    No Known Activations