© 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. 7074
    Prev
    Next
    INDEX
    Explanations

    text that discusses measurement or quantifiable parameters, particularly within a normal or expected scope

    oai_token-act-pair · gemini-2.0-flash

    acceptable, healthy, ideal

    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
     Monfieur
    -0.72
     greateſt
    -0.67
    AndEndTag
    -0.66
    RenderAtEndOf
    -0.62
     OFDb
    -0.61
     erbjud
    -0.61
     purpoſe
    -0.60
     Paglinawan
    -0.60
    GeneratedCode
    -0.60
     skär
    -0.60
    POSITIVE LOGITS
     comfortable
    0.87
     healthy
    0.80
     ideal
    0.69
     Comfortable
    0.60
     safe
    0.59
     reasonable
    0.59
    comfortable
    0.59
    healthy
    0.59
     recommended
    0.58
     appropriate
    0.58
    Activations Density 1.756%

    No Known Activations