© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10745
    Prev
    Next
    INDEX
    Explanations

    acronyms and initialisms of commands, parameters or concepts across different domains like networking, programming, science or statistics

    oai_token-act-pair · gemini-2.0-flash

    initial letter pairings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     AssemblyCulture
    -0.95
    __':
    -0.81
    TagMode
    -0.79
    WithIOException
    -0.77
    InteropServices
    -0.76
    ]<<"
    -0.75
    StructEnd
    -0.74
     препратки
    -0.74
    Abitanti
    -0.73
    expandindo
    -0.73
    POSITIVE LOGITS
    red
    0.48
     red
    0.43
    oly
    0.43
     кра
    0.43
    ty
    0.41
    ש
    0.41
    Red
    0.40
    od
    0.40
    he
    0.39
    el
    0.39
    Activations Density 6.432%

    No Known Activations