© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11949
    Prev
    Next
    INDEX
    Explanations

    references to divisions and separations

    oai_token-act-pair · gemini-2.0-flash

    separate or own

    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
    -1.34
     EconPapers
    -1.17
     raiſ
    -1.15
     Efq
    -1.09
    contentLoaded
    -1.09
     otomatig
    -1.08
     myſelf
    -1.06
     CreateTagHelper
    -1.01
     houſe
    -0.98
    ImageContext
    -0.98
    POSITIVE LOGITS
     
    0.56
     K
    0.47
    -
    0.46
    ,
    0.46
     New
    0.45
     r
    0.44
    .
    0.44
     k
    0.43
     C
    0.43
     P
    0.42
    Activations Density 1.606%

    No Known Activations