© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7174
    Prev
    Next
    INDEX
    Explanations

    articles "a" or "the" followed by adjectives and nouns that describe how something looks, feels, or functions.

    oai_token-act-pair · gemini-2.0-flash

    descriptions of objects

    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
    Negative Logits
     a
    -0.76
     an
    -0.62
     faveur
    -0.49
     the
    -0.48
     referenties
    -0.48
    弄
    -0.48
     («
    -0.44
    ,
    -0.44
     perciò
    -0.44
     Référence
    -0.44
    POSITIVE LOGITS
    IRQn
    0.65
    LLocation
    0.65
     <=",
    0.62
     INTERESAR
    0.61
     nocturne
    0.60
     smoother
    0.60
    RenderAtEndOf
    0.59
     thicker
    0.58
     humide
    0.58
    TagMode
    0.58
    Activations Density 1.009%

    No Known Activations