© 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. 82
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     AssemblyCompany
    -0.56
    \{\\
    -0.52
      
    -0.51
      
    -0.49
     –,
    -0.48
    RenderAtEndOf
    -0.47
    хьтан
    -0.47
     ―
    -0.47
    __":
    -0.47
    soever
    -0.46
    POSITIVE LOGITS
    forhold
    0.56
     virš
    0.48
     stället
    0.47
     scolaires
    0.47
     årene
    0.46
     agujero
    0.45
     vectorielles
    0.44
     frequenza
    0.44
     attrs
    0.43
     nød
    0.43
    Activations Density 38.802%

    No Known Activations