© 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. 11182
    Prev
    Next
    INDEX
    Explanations

    technical writing, especially related to a scientific invention or discovery

    oai_token-act-pair · gemini-2.0-flash

    part variants

    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
    GEBURTSDATUM
    -0.91
    ScopeManager
    -0.80
    TintMode
    -0.75
    LLocation
    -0.73
     Мексичка
    -0.73
    #+#
    -0.72
     Roskov
    -0.69
     AssemblyCompany
    -0.69
     Superhost
    -0.68
    曖昧さ回避
    -0.66
    POSITIVE LOGITS
     part
    3.63
    part
    3.17
    Part
    2.83
     parte
    2.73
     Part
    2.64
     parts
    2.47
     PART
    2.27
    parts
    2.20
     часть
    2.17
     Teil
    2.09
    Activations Density 6.839%

    No Known Activations