© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4275
    Prev
    Next
    INDEX
    Explanations

    words describing community involvement, cohesion, and collaboration in professional settings.

    oai_token-act-pair · gemini-2.0-flash

    facilitating or improving services

    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
     houſe
    -0.89
     Anſ
    -0.88
     Houſe
    -0.87
     myſelf
    -0.84
     Theſe
    -0.83
     pinulongan
    -0.82
     Reſ
    -0.80
     ſte
    -0.80
     ainfi
    -0.80
     ſtate
    -0.79
    POSITIVE LOGITS
     chắn
    0.37
     sen
    0.36
    n
    0.36
    ‌
    0.36
    ades
    0.35
    )|
    0.35
    منابع
    0.34
    ungo
    0.32
    во
    0.32
     fle
    0.32
    Activations Density 5.455%

    No Known Activations