© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4333
    Prev
    Next
    INDEX
    Explanations

    terms related to historical events, particularly battles and reigns of power

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms and code elements

    np_token-act-pair-logits · gpt-4o-mini

    historical events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ardless
    -0.67
    Попис
    -0.62
    FieldBuilder
    -0.58
     instituições
    -0.57
    ,:]
    -0.57
     tauto
    -0.55
    ntlet
    -0.55
     ListTile
    -0.54
     suicides
    -0.54
     Handmaid
    -0.53
    POSITIVE LOGITS
    OptionsMenu
    0.52
    styleUrls
    0.50
    Hochspringen
    0.50
    estar
    0.48
    ViewChild
    0.47
    IBOutlet
    0.44
    RegressionTest
    0.44
     яйцо
    0.42
     mergeFrom
    0.42
     exc
    0.42
    Activations Density 0.595%

    No Known Activations