© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13681
    Prev
    Next
    INDEX
    Explanations

    terms related to people, growth, and change

    oai_token-act-pair · gemini-2.0-flash

    Movement and change

    np_max-act-logits · gemini-2.0-flash

    say "verbs"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RectangleBorder
    -0.71
     AppColors
    -0.66
     varandra
    -0.66
    BagLayout
    -0.65
    }))
    -0.63
     feroit
    -0.63
     fédé
    -0.61
    MLLoader
    -0.61
     purpoſe
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    POSITIVE LOGITS
     come
    1.10
     grow
    1.01
     go
    0.98
     emerge
    0.92
     enter
    0.88
     disappear
    0.88
     fall
    0.87
     take
    0.86
     arrive
    0.85
     become
    0.83
    Activations Density 2.384%

    No Known Activations