© 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. 12538
    Prev
    Next
    INDEX
    Explanations

    words that soften claims and connect ideas

    oai_token-act-pair · gemini-2.0-flash

    actually

    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
    GTCX
    -0.47
    樣子
    -0.41
    GAP
    -0.41
    <eos>
    -0.41
    otti
    -0.41
     spagnolo
    -0.40
    ordinator
    -0.40
    blos
    -0.39
    ]<<"
    -0.39
     чем
    -0.39
    POSITIVE LOGITS
     Савезне
    0.71
    DoubleQuotes
    0.69
     oprot
    0.68
    IsMutable
    0.66
    WindowConstants
    0.65
    )))));
    0.63
     nahilalakip
    0.60
    clusal
    0.60
    XmlAccessType
    0.60
    roek
    0.59
    Activations Density 0.291%

    No Known Activations