© 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. 604
    Prev
    Next
    INDEX
    Explanations

    titles and descriptors of people such as "chief", "magistrate," "leader," and "secretary."

    oai_token-act-pair · gemini-2.0-flash

    government officials and events

    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
    ://
    -0.49
     Ruy
    -0.47
     Rouge
    -0.46
     ints
    -0.46
    rø
    -0.45
     LIV
    -0.45
     Mestre
    -0.45
     gonzález
    -0.44
    Bioaccumulative
    -0.43
    Rog
    -0.43
    POSITIVE LOGITS
     InputDecoration
    0.78
     autorytatywna
    0.75
    httphttps
    0.74
    expandindo
    0.73
    Tikang
    0.72
    Personendaten
    0.72
    tagHelperRunner
    0.70
    adaptiveStyles
    0.69
    Попис
    0.69
    Rhestr
    0.68
    Activations Density 3.225%

    No Known Activations