© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3845
    Prev
    Next
    INDEX
    Explanations

    references, especially years and abbreviated names

    oai_token-act-pair · gemini-2.0-flash

    9 and 7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     iconFacebook
    -0.60
    جانب
    -0.54
     (\<
    -0.53
    กลาง
    -0.52
     sesama
    -0.51
     myſelf
    -0.51
     $_"
    -0.50
     "\<
    -0.50
     thereto
    -0.49
     itſelf
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    1.03
    出版年
    1.02
     kasarigan
    1.02
    RegistryLite
    0.85
     createSlice
    0.85
    httphttps
    0.82
    interopRequire
    0.79
    GEBURTSDATUM
    0.78
    didSet
    0.77
    SharedCtor
    0.77
    Activations Density 1.643%

    No Known Activations