© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15361
    Prev
    Next
    INDEX
    Explanations

    positive testimonials, reviews and other content demonstrating approval.

    oai_token-act-pair · gemini-2.0-flash

    Web-related context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    клопе
    -0.67
    $}}
    -0.65
     Biôgrafia
    -0.63
    ]='\
    -0.62
    حياته
    -0.60
    ]";
    -0.60
    Rhestr
    -0.59
    новништво
    -0.58
     történ
    -0.57
     חיצוניים
    -0.57
    POSITIVE LOGITS
     Webcam
    0.50
    izielle
    0.48
     gu
    0.47
    astu
    0.47
    angi
    0.47
     paso
    0.46
    ंदीखरीदारी
    0.46
     Members
    0.46
    рс
    0.45
     Whitehall
    0.44
    Activations Density 24.856%

    No Known Activations