© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3344
    Prev
    Next
    INDEX
    Explanations

    technical academic text about circuit complexity and algorithms including terms like "tree width", "circuits", "Boolean", "algorithm" and "exponential".

    oai_token-act-pair · gemini-2.0-flash

    research paper excerpts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.74
    MethodManager
    -0.72
    ModelAdmin
    -0.65
    aarrggbb
    -0.64
    ыгана
    -0.61
     مشين
    -0.61
    ModelSerializer
    -0.61
    GHIJKLM
    -0.59
    afficheront
    -0.59
    كويكب
    -0.59
    POSITIVE LOGITS
     hyö
    0.54
    солю
    0.52
     kysy
    0.50
     parem
    0.48
     enemmän
    0.48
    Instance
    0.47
     henkil
    0.45
     privées
    0.44
     personlig
    0.44
     lisäksi
    0.43
    Activations Density 8.343%

    No Known Activations