© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13140
    Prev
    Next
    INDEX
    Explanations

    mentions of remembering, learning, mentioning or admitting something.

    oai_token-act-pair · gemini-2.0-flash

    questions or prompts for explanation

    np_token-act-pair-logits · gpt-4o-mini

    remember/forget

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kasarigan
    -0.57
    Dougall
    -0.48
    roek
    -0.46
    OY
    -0.46
     Оно
    -0.45
    buya
    -0.44
    ItemStack
    -0.42
    leştir
    -0.41
    lismo
    -0.41
    bury
    -0.40
    POSITIVE LOGITS
     how
    0.90
     why
    0.77
     propOrder
    0.71
     which
    0.71
     to
    0.70
     what
    0.69
    addCriterion
    0.69
    MLLoader
    0.65
    PerformLayout
    0.65
     FetchType
    0.64
    Activations Density 3.005%

    No Known Activations