© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12243
    Prev
    Next
    INDEX
    Explanations

    code snippets and data structures

    oai_token-act-pair · gemini-2.0-flash

    code and addresses

    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
    AnimationsModule
    -0.65
    InputBorder
    -0.63
     BoxDecoration
    -0.60
    :]:
    -0.60
    UnknownFields
    -0.59
     Roskov
    -0.57
    Obrázky
    -0.54
    UIL
    -0.54
    )_/¯
    -0.54
     ویکی‌پدیا
    -0.53
    POSITIVE LOGITS
     quelconque
    0.49
    veness
    0.49
    BeginContext
    0.49
     חיצוניים
    0.49
     transferencia
    0.48
    וויק
    0.47
    şek
    0.46
     entanto
    0.46
    IntoConstraints
    0.45
    bonucleic
    0.45
    Activations Density 1.001%

    No Known Activations