© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1953
    Prev
    Next
    INDEX
    Explanations

    technical language from various fields

    oai_token-act-pair · gemini-2.0-flash

    reporting events/situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Efq
    -1.45
     Majefty
    -1.22
    ſelf
    -1.20
     itſelf
    -1.18
     Jefus
    -1.18
    complexContent
    -1.13
     Monfieur
    -1.12
     Chriftian
    -1.11
    ſelves
    -1.10
     ―――――
    -1.09
    POSITIVE LOGITS
     
    0.69
     may
    0.64
     (
    0.62
     Ne
    0.61
     p
    0.60
     Ar
    0.58
     _
    0.57
    ↵
    0.57
     All
    0.55
     P
    0.54
    Activations Density 8.931%

    No Known Activations