© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1973
    Prev
    Next
    INDEX
    Explanations

    short, common words such as "to," "up," "of," "the," and "with."

    oai_token-act-pair · gemini-2.0-flash

    How-to guides

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     незавершена
    -0.64
    +#+#
    -0.59
    parsedMessage
    -0.56
    PyExc
    -0.55
    TestingModule
    -0.55
    ParallelGroup
    -0.55
    UrlResolution
    -0.54
    DebuggerNonUser
    -0.52
     CURIAM
    -0.52
    kaner
    -0.52
    POSITIVE LOGITS
     Bring
    0.98
     Apply
    0.92
     Make
    0.90
     Eat
    0.84
     Give
    0.84
     Keep
    0.84
     Take
    0.84
     Remove
    0.82
    Apply
    0.82
     Create
    0.82
    Activations Density 2.641%

    No Known Activations