© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4545
    Prev
    Next
    INDEX
    Explanations

    language about business to customer relations including social media marketing and customer engagement.

    oai_token-act-pair · gemini-2.0-flash

    business and customers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IonicModule
    -1.16
     nahilalakip
    -1.13
     ModelExpression
    -1.02
    SharedDtor
    -0.95
     ſeveral
    -0.94
     تضيفلها
    -0.91
     itſelf
    -0.88
     myſelf
    -0.88
    setVerticalGroup
    -0.86
    NUMX
    -0.85
    POSITIVE LOGITS
    chtes
    0.47
     brand
    0.41
    initWithFrame
    0.38
    dika
    0.38
     real
    0.37
     Real
    0.36
    ello
    0.36
     brands
    0.35
    amo
    0.35
    real
    0.35
    Activations Density 2.231%

    No Known Activations