© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5083
    Prev
    Next
    INDEX
    Explanations

    words related to principles or building blocks that support a main idea

    oai_token-act-pair · gemini-2.0-flash

    foundational elements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rdı
    -0.62
    fjspx
    -0.61
    żesz
    -0.60
    GEBURTSDATUM
    -0.59
    TypedDataSet
    -0.59
    ImageContext
    -0.58
     MessageBoxIcon
    -0.58
    ContentAsync
    -0.58
    setArguments
    -0.56
    FailureListener
    -0.55
    POSITIVE LOGITS
    JvmStatic
    0.52
    hart
    0.47
     tartalomajánló
    0.44
    춤
    0.44
    //</
    0.44
    ])):
    0.43
    trib
    0.41
    Poz
    0.40
     RUM
    0.40
    expandindo
    0.40
    Activations Density 8.080%

    No Known Activations