© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9519
    Prev
    Next
    INDEX
    Explanations

    dashes or forward slashes separating numbers, as often found in URLs or UUIDs

    oai_token-act-pair · gemini-2.0-flash

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     dipl
    -0.53
    bakken
    -0.52
     verden
    -0.52
     marques
    -0.50
     насеље
    -0.49
    ru
    -0.47
    ren
    -0.47
    RTEX
    -0.47
    Domain
    -0.47
     lég
    -0.47
    POSITIVE LOGITS
    AnchorStyles
    0.87
    styleType
    0.84
     defaultstate
    0.77
     '\\;'
    0.77
     disambiguazione
    0.77
    verwijspagina
    0.74
    "]);
    0.73
    ArrowToggle
    0.72
     désolés
    0.72
    DeleteBehavior
    0.71
    Activations Density 1.953%

    No Known Activations