© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13489
    Prev
    Next
    INDEX
    Explanations

    summary tags and related markup (likely XML)

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    cenzo
    -0.56
    VersionUID
    -0.49
    odend
    -0.47
    mopol
    -0.47
    chability
    -0.46
    Сі
    -0.44
    ernalia
    -0.44
    alanx
    -0.43
    AGAN
    -0.43
    uggle
    -0.42
    POSITIVE LOGITS
    awtextra
    0.69
    Explicación
    0.67
     AssemblyTitle
    0.66
    ValueGenerated
    0.66
    Hentet
    0.65
    homonymie
    0.59
    SuspendLayout
    0.58
     pleins
    0.57
     quæ
    0.57
     Процитовано
    0.57
    Activations Density 1.563%

    No Known Activations