© 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. 13250
    Prev
    Next
    INDEX
    Explanations

    mentions of VPNs, pills, and inflex, especially as related to cost and location

    oai_token-act-pair · gemini-2.0-flash

    VPN and countries

    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
     Audiodateien
    -0.83
    :✨
    -0.76
     referrerpolicy
    -0.67
    Viitteet
    -0.66
    tagext
    -0.65
    stalt
    -0.64
    IsMutable
    -0.60
    ">//
    -0.60
    setVerticalGroup
    -0.60
    LookAnd
    -0.59
    POSITIVE LOGITS
    Населення
    0.54
    lhes
    0.50
     initWithFrame
    0.48
     Sohn
    0.47
    heça
    0.47
    owano
    0.47
    kirchen
    0.46
    ագրություններ
    0.45
    Quellen
    0.45
    قایناقلار
    0.44
    Activations Density 0.022%

    No Known Activations