© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12453
    Prev
    Next
    INDEX
    Explanations

    words related to veterinary medicine and types of animals.

    oai_token-act-pair · gemini-2.0-flash

    animal species and conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     consultato
    -0.64
    endpush
    -0.63
     stället
    -0.60
     roulant
    -0.57
    getDriver
    -0.55
     StatefulWidget
    -0.55
    sizeof
    -0.55
    értelmű
    -0.54
     pilote
    -0.54
    abstractmethod
    -0.54
    POSITIVE LOGITS
    Jeografia
    0.59
     pinulongan
    0.56
    Enllaces
    0.54
     oprot
    0.53
    LLocation
    0.53
    TintMode
    0.51
    جمعیت
    0.46
    JspWriter
    0.45
     يتيمه
    0.45
    Forty
    0.45
    Activations Density 0.717%

    No Known Activations