© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12086
    Prev
    Next
    INDEX
    Explanations

    miscellaneous words and numbers that frequently occur together

    oai_token-act-pair · gemini-2.0-flash

    International issues/legal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     damals
    -0.58
    zelfde
    -0.57
    :✨
    -0.57
     mesmas
    -0.51
     same
    -0.50
    那时候
    -0.50
    那时
    -0.50
    Same
    -0.49
     last
    -0.49
     Last
    -0.48
    POSITIVE LOGITS
    TagMode
    0.91
    __(/*!
    0.74
    bootstrapcdn
    0.71
     BoxDecoration
    0.70
    +#+
    0.69
     surla
    0.66
    endphp
    0.65
    /*
    0.65
    AxisAlignment
    0.64
    SourceChecksum
    0.64
    Activations Density 3.850%

    No Known Activations