© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12786
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain certain keywords and structural elements like if/else

    oai_token-act-pair · gemini-2.0-flash

    colons and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    MENAFN
    -0.84
     INTERESAR
    -0.64
    ureusement
    -0.63
     Lumpur
    -0.58
     
    -0.58
    rawDesc
    -0.57
    ettür
    -0.57
     Pendleton
    -0.56
     chains
    -0.56
     саны
    -0.56
    POSITIVE LOGITS
     Vikipedi
    0.49
    Jereo
    0.43
     spiegel
    0.42
    "
    0.42
    LookAnd
    0.41
     adev
    0.39
     definição
    0.39
    XmlEnum
    0.38
    不着
    0.38
     viewType
    0.38
    Activations Density 0.282%

    No Known Activations