© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14154
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in marketing new digital devices.

    oai_token-act-pair · gemini-2.0-flash

    phones and apps

    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
    ⓧ
    -0.66
    InjectAttribute
    -0.60
    PhysRevD
    -0.53
    허
    -0.51
     <<<<<<<<<<<<<<
    -0.51
    MemoryWarning
    -0.49
     незавершена
    -0.48
    ardes
    -0.48
    waitKey
    -0.47
    Jedis
    -0.45
    POSITIVE LOGITS
     Italijanski
    0.64
    endphp
    0.61
     Efq
    0.59
    oł
    0.57
    kháu
    0.55
     Morph
    0.55
     aze
    0.53
     SIA
    0.51
     catholic
    0.51
     Rival
    0.51
    Activations Density 1.683%

    No Known Activations