© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2436
    Prev
    Next
    INDEX
    Explanations

    measurements written with numbers and units

    oai_token-act-pair · gemini-2.0-flash

    Measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Monfieur
    -0.93
     Efq
    -0.89
     Majefty
    -0.84
     myſelf
    -0.83
    writeFieldEnd
    -0.77
     themſelves
    -0.72
     becauſe
    -0.71
     ſmall
    -0.71
     leaſt
    -0.70
     Jefus
    -0.69
    POSITIVE LOGITS
    GraphicsUnit
    0.61
    cm
    0.58
    ReusableCell
    0.56
     onOptions
    0.54
    in
    0.52
    enumi
    0.48
    ec
    0.47
    .
    0.47
    kmal
    0.47
    uc
    0.47
    Activations Density 5.061%

    No Known Activations