© 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. 12231
    Prev
    Next
    INDEX
    Explanations

    a variety of technical terms, many from science and engineering

    oai_token-act-pair · gemini-2.0-flash

    technical or foreign content

    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
     md
    -0.84
     cd
    -0.84
     rv
    -0.83
     cs
    -0.81
     fm
    -0.81
     lp
    -0.80
     rc
    -0.79
     mc
    -0.77
     ct
    -0.77
     m
    -0.77
    POSITIVE LOGITS
     aikaa
    0.88
     vastaan
    0.87
     strøm
    0.84
     jäsen
    0.82
     löytyy
    0.79
     elä
    0.78
     szív
    0.78
     väli
    0.78
     näky
    0.77
     päivä
    0.77
    Activations Density 47.280%

    No Known Activations