© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14177
    Prev
    Next
    INDEX
    Explanations

    scientific writing using the passive voice including verbs like 'seen', 'made', 'using', 'available', and ' yield'

    oai_token-act-pair · gemini-2.0-flash

    scientific observations

    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
    iffion
    -0.71
    UIControlState
    -0.70
    Czytaj
    -0.69
    CloseOperation
    -0.69
    GOTREF
    -0.68
     ExecuteAsync
    -0.67
     cauſe
    -0.66
    didSet
    -0.66
     дописавши
    -0.65
    DockStyle
    -0.64
    POSITIVE LOGITS
    rible
    0.54
     empezó
    0.52
    --
    0.50
    pierw
    0.49
    NavController
    0.48
    H
    0.48
     everybody
    0.47
    der
    0.47
    cyd
    0.47
    ↵↵
    0.47
    Activations Density 6.154%

    No Known Activations