© 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. 15539
    Prev
    Next
    INDEX
    Explanations

    words or parts of words, particularly verbs, from other languages within English text, as well as some code-related terms

    oai_token-act-pair · gemini-2.0-flash

    code and language snippets

    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
    GEBURTSDATUM
    -0.70
    ")));
    -0.63
    
    -0.63
     got
    -0.60
    "]]
    -0.58
    '))
    -0.57
     followed
    -0.56
    setVerticalGroup
    -0.56
    '));
    -0.56
    ')));
    -0.54
    POSITIVE LOGITS
    ulative
    0.51
     jej
    0.49
    alo
    0.45
    BuildContext
    0.44
    hoz
    0.43
    nal
    0.43
     holographic
    0.43
    sió
    0.43
     عظ
    0.42
     absl
    0.42
    Activations Density 1.700%

    No Known Activations