© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8233
    Prev
    Next
    INDEX
    Explanations

    code snippets related to defining constants or variables, especially those starting with "G", "V", or "F"

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'g'

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

    g

    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
    GEBURTSDATUM
    -0.66
    PreferredItem
    -0.65
    viewWillAppear
    -0.62
    onActivityResult
    -0.57
     viewDidLoad
    -0.55
    thday
    -0.54
     diem
    -0.53
    tedly
    -0.53
    cleo
    -0.53
    parsedMessage
    -0.52
    POSITIVE LOGITS
    saraba
    0.68
    OGND
    0.57
     terk
    0.52
     Económica
    0.50
    expandindo
    0.49
     tslint
    0.49
    CloseOperation
    0.46
    ponses
    0.46
     Constitucional
    0.46
     تضيفلها
    0.45
    Activations Density 1.294%

    No Known Activations