© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8130
    Prev
    Next
    INDEX
    Explanations

    the letters "fe" or "ef", sometimes in words, sometimes as random characters

    oai_token-act-pair · gemini-2.0-flash

    fe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    seven
    -0.57
    re
    -0.56
    real
    -0.56
    right
    -0.53
    doi
    -0.53
    stamp
    -0.53
    égard
    -0.53
    rest
    -0.51
    sell
    -0.51
    res
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.68
     cherchés
    0.64
    RegistryLite
    0.60
    principalTable
    0.60
    eee
    0.56
     متعلقه
    0.56
     betweenstory
    0.54
    RenderAtEndOf
    0.54
    SpringRunner
    0.52
    BagLayout
    0.51
    Activations Density 2.589%

    No Known Activations