© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8030
    Prev
    Next
    INDEX
    Explanations

    timestamp and date formats with separators

    oai_token-act-pair · gemini-2.0-flash

    non-standard tokens or syntax

    np_token-act-pair-logits · gpt-4o-mini

    hyphens and slashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
      (
    -0.64
     vidare
    -0.59
     January
    -0.58
     Roskov
    -0.58
     Jan
    -0.58
    SharedCtor
    -0.57
    DebuggerNonUser
    -0.57
     referenties
    -0.57
    Portály
    -0.56
    addCriterion
    -0.55
    POSITIVE LOGITS
    verwijspagina
    0.57
    wapV
    0.53
    uxxxx
    0.52
    
    0.47
     Lump
    0.45
     bParam
    0.44
    FormsModule
    0.44
     defStyle
    0.44
    MeasureSpec
    0.43
    ydı
    0.43
    Activations Density 1.027%

    No Known Activations