© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    text from online forum or community posts referencing personal electronics and online activity

    oai_token-act-pair · gemini-2.0-flash

    phones and electronics

    np_max-act-logits · gemini-2.0-flash
    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
    الحياه
    -0.70
    
    -0.64
     jadx
    -0.63
    Referanser
    -0.62
     مشين
    -0.61
    DebuggerNonUser
    -0.60
     AssemblyProduct
    -0.60
    IsMutable
    -0.59
    ViewFeatures
    -0.59
     चीज़ों
    -0.58
    POSITIVE LOGITS
     Waray
    0.57
    setupUi
    0.57
    acies
    0.53
    SSON
    0.52
    getMap
    0.51
    ntgen
    0.51
    fsen
    0.50
    ̍t
    0.50
     تانيه
    0.49
     ↓,
    0.49
    Activations Density 1.868%

    No Known Activations