© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10568
    Prev
    Next
    INDEX
    Explanations

    words related to events, festivals, writing, and literature, particularly related to political and social themes.

    oai_token-act-pair · gemini-2.0-flash

    Descriptive summaries

    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
    ChildScrollView
    -0.56
    __))
    -0.53
    تقاوى
    -0.52
    "]);
    -0.50
    /*
    -0.50
    "])
    -0.49
    '}),
    -0.48
    raborty
    -0.46
     BoxFit
    -0.45
    ."],
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.65
    ArrowToggle
    0.59
    ConstraintMaker
    0.59
    Ссылки
    0.55
    Mvc
    0.53
    typeparam
    0.53
    RectangleBorder
    0.53
     fleste
    0.52
    lewati
    0.52
     bäst
    0.52
    Activations Density 3.765%

    No Known Activations