© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12228
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and ideas related to the impact one person or group of people can have on another

    oai_token-act-pair · gemini-2.0-flash

    abstract concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    tagHelper
    -0.60
    irvana
    -0.60
    twimg
    -0.58
    Lähteet
    -0.54
    copg
    -0.53
    estacks
    -0.53
    tomans
    -0.52
    URUS
    -0.50
     onCreateView
    -0.50
    onicus
    -0.49
    POSITIVE LOGITS
     whoſe
    0.69
     themſelves
    0.64
     itſelf
    0.63
    SourceChecksum
    0.58
     deſt
    0.58
     iſt
    0.54
     ſy
    0.54
     againſt
    0.53
    AddTagHelper
    0.52
     Wikimedijinoj
    0.52
    Activations Density 2.750%

    No Known Activations