© 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. 11699
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to error handling, conditions, and loops

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    iotti
    -0.50
    اد
    -0.49
    ticia
    -0.47
     basket
    -0.47
    lowy
    -0.42
    readInt
    -0.41
    男子
    -0.41
    textbackslash
    -0.41
    SMB
    -0.40
     Norden
    -0.40
    POSITIVE LOGITS
    WriteTagHelper
    0.90
    IndentedString
    0.89
    LookAnd
    0.81
     Italijanski
    0.81
     <=",
    0.79
    şiv
    0.79
     Paglinawan
    0.77
     Савезне
    0.76
    oredCriteria
    0.75
    RegistryLite
    0.74
    Activations Density 1.041%

    No Known Activations