© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 203
    Prev
    Next
    INDEX
    Explanations

    angle brackets around words with the suffix "es"

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    :+:
    -0.64
    makeConstraints
    -0.56
     bezeichneter
    -0.55
    ########.
    -0.55
     lenker
    -0.54
    TestingModule
    -0.50
    ]")]
    -0.50
    IsMutable
    -0.49
    Datuak
    -0.48
    лтамалар
    -0.48
    POSITIVE LOGITS
     يتيمه
    0.57
    ThemeOverlay
    0.54
     Verified
    0.54
     Intensi
    0.54
    cuno
    0.51
    DESCRIPTOR
    0.51
     adjoint
    0.50
    ὗ
    0.50
     Sunlight
    0.50
    HttpMethod
    0.49
    Activations Density 57.834%

    No Known Activations