© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8687
    Prev
    Next
    INDEX
    Explanations

    the character sequences "780", "781", and escape sequences starting with "xe"

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     الحره
    -0.81
    nodoc
    -0.73
     betweenstory
    -0.73
    SharedDtor
    -0.68
     ujednoznacz
    -0.68
    __*/
    -0.64
    Geplaatst
    -0.63
    ContentAsync
    -0.60
    GIH
    -0.60
    enderal
    -0.59
    POSITIVE LOGITS
     numbering
    0.46
     contre
    0.46
     contra
    0.43
     partial
    0.42
    roach
    0.41
    mės
    0.41
    partial
    0.41
    рано
    0.40
     "..\..\
    0.40
    әрмәләр
    0.39
    Activations Density 1.101%

    No Known Activations