© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11966
    Prev
    Next
    INDEX
    Explanations

    technical or medical writing, looking for descriptions of processes or treatments.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ISupport
    -0.79
    RegistryLite
    -0.70
    EndInit
    -0.68
    Переваги
    -0.67
    ArrowToggle
    -0.67
     chi̍t
    -0.67
    IUrlHelper
    -0.66
     للمعارف
    -0.64
    ̍t
    -0.64
     nahilalakip
    -0.62
    POSITIVE LOGITS
     ins
    0.54
    Ins
    0.50
     Ins
    0.50
     En
    0.50
    En
    0.47
     en
    0.42
     mandate
    0.42
     block
    0.42
    +:+
    0.41
    ment
    0.40
    Activations Density 4.708%

    No Known Activations