© 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. 9412
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    x

    np_max-act-logits · gemini-2.0-flash

    x

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     &
    -0.66
    <h3>
    -0.59
     Itself
    -0.53
     and
    -0.52
    /</
    -0.50
    <h2>
    -0.48
     themselves
    -0.48
     \&
    -0.48
    itself
    -0.46
     itself
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.89
    IntoConstraints
    0.85
    tagHelperRunner
    0.84
    SharedCtor
    0.81
    IndentedString
    0.79
    GEBURTSDATUM
    0.78
    SBATCH
    0.75
     calendriers
    0.73
    GEBURTS
    0.71
     AssemblyProduct
    0.70
    Activations Density 14.692%

    No Known Activations