© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6130
    Prev
    Next
    INDEX
    Explanations

    mentions of goals, intentions, or desired outcomes, and html list tags

    oai_token-act-pair · gemini-2.0-flash

    objective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -0.64
     --
    -0.59
     Li
    -0.58
    Li
    -0.58
    li
    -0.57
     li
    -0.56
    .
    -0.55
     &&
    -0.55
     (
    -0.54
    (
    -0.52
    POSITIVE LOGITS
    ſelf
    1.05
     itſelf
    1.05
    ſelves
    0.99
     Theſe
    0.96
     purpoſe
    0.94
    NUMX
    0.91
     houſe
    0.90
     pleaſure
    0.90
     Majefty
    0.88
     Efq
    0.88
    Activations Density 1.060%

    No Known Activations