© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15565
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating factual correctness

    oai_token-act-pair · gemini-2.0-flash

    true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Lichten
    -0.57
    PerformLayout
    -0.56
    enumi
    -0.54
    irical
    -0.53
    persky
    -0.52
     Arguments
    -0.52
     precedents
    -0.52
    TextHelper
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    efte
    -0.51
    POSITIVE LOGITS
    ungguhnya
    0.50
     الأصل
    0.50
    realloc
    0.49
     trữ
    0.48
     sebenar
    0.47
    ostante
    0.46
    __*/
    0.46
    قيقي
    0.46
    verdad
    0.46
    şiv
    0.44
    Activations Density 2.852%

    No Known Activations