© 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. 3519
    Prev
    Next
    INDEX
    Explanations

    the name "Mencken".

    oai_token-act-pair · gemini-2.0-flash

    men

    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
    WebElementEntity
    -0.79
     AssemblyCulture
    -0.77
     שוליים
    -0.70
    tvguidetime
    -0.70
    Билгалдахарш
    -0.69
     Савезне
    -0.69
     mergeFrom
    -0.68
    Попис
    -0.68
    addCriterion
    -0.67
    InjectAttribute
    -0.65
    POSITIVE LOGITS
    nell
    0.44
    oplayer
    0.44
    dem
    0.43
    iert
    0.42
     cabecera
    0.42
    cher
    0.41
    <!--
    0.40
     Care
    0.40
    ิน
    0.40
     quartiere
    0.40
    Activations Density 1.401%

    No Known Activations