© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10652
    Prev
    Next
    INDEX
    Explanations

    common English words, sometimes forming simple phrases, with a slight tendency to activate more on negated clauses

    oai_token-act-pair · gemini-2.0-flash

    gibberish

    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
     שוליים
    -0.83
     myſelf
    -0.82
     ujednoznacz
    -0.82
    contentLoaded
    -0.80
     Efq
    -0.79
    ValueStyle
    -0.79
    twimg
    -0.78
    MigrationBuilder
    -0.77
     raiſ
    -0.77
    +#+#
    -0.75
    POSITIVE LOGITS
     an
    3.03
    An
    1.61
     An
    1.53
    an
    1.53
     aan
    1.23
     AN
    1.14
     daran
    0.96
     anex
    0.69
    AN
    0.69
     degli
    0.62
    Activations Density 5.266%

    No Known Activations