© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3804
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to experiment results

    oai_token-act-pair · gemini-2.0-flash

    Emphasizing/highlighting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    djangoproject
    -1.09
    发表于
    -0.82
     يتيمه
    -0.78
    cshtml
    -0.76
    tvguidetime
    -0.73
     AttributeSet
    -0.72
     AssemblyCulture
    -0.72
    RenderAtEndOf
    -0.71
     للمعارف
    -0.71
     Мексичка
    -0.71
    POSITIVE LOGITS
     muita
    0.45
    ing
    0.43
     fourrure
    0.40
     claras
    0.40
     sauvages
    0.39
    icing
    0.39
     malattie
    0.39
     the
    0.39
    end
    0.38
     Catto
    0.38
    Activations Density 2.339%

    No Known Activations