© 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. 11082
    Prev
    Next
    INDEX
    Explanations

    a variety of technical terms related to science, politics, and electronics.

    oai_token-act-pair · gemini-2.0-flash

    "an" and "und"

    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
    BeginContext
    -0.57
    السكان
    -0.49
    invokeLater
    -0.47
    ValueStyle
    -0.46
    jspb
    -0.45
    oredCriteria
    -0.44
    rinfo
    -0.44
     CWE
    -0.44
    клопе
    -0.44
    География
    -0.43
    POSITIVE LOGITS
     an
    2.53
     und
    1.48
    an
    1.42
    An
    1.20
     An
    1.05
    Und
    1.05
    und
    1.03
     AN
    0.94
     anf
    0.93
     anex
    0.93
    Activations Density 20.595%

    No Known Activations