© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13958
    Prev
    Next
    INDEX
    Explanations

    words ending in 's' that are superlatives or possessives, especially those associated with global contexts

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     AssemblyProduct
    -0.79
     propOrder
    -0.77
    исленность
    -0.77
    StoryboardSegue
    -0.73
     للمعارف
    -0.71
     gyhoeddwyd
    -0.69
    providedIn
    -0.68
    Personendaten
    -0.68
    ArrowToggle
    -0.68
     resourceCulture
    -0.66
    POSITIVE LOGITS
     froh
    0.45
     whereupon
    0.44
     onOptions
    0.43
     dennoch
    0.41
     -=
    0.41
     nada
    0.41
    setattr
    0.41
     thus
    0.39
    First
    0.39
    Leftrightarrow
    0.39
    Activations Density 4.879%

    No Known Activations