© 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. 5096
    Prev
    Next
    INDEX
    Explanations

    a variety of keywords that occur in natural language

    oai_token-act-pair · gemini-2.0-flash

    Varied text sources

    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
     gând
    -0.55
     (
    -0.50
     
    -0.46
     suun
    -0.46
    ')(
    -0.46
     păr
    -0.45
     hű
    -0.45
    /
    -0.44
     szív
    -0.44
    ")(
    -0.44
    POSITIVE LOGITS
     Efq
    0.73
     ſeveral
    0.73
     الحره
    0.73
     myſelf
    0.71
     itſelf
    0.67
     يتيمه
    0.66
     للمعارف
    0.65
     raiſ
    0.64
     himſelf
    0.63
    ſelves
    0.62
    Activations Density 16.710%

    No Known Activations