© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13795
    Prev
    Next
    INDEX
    Explanations

    years and superlatives

    oai_token-act-pair · gemini-2.0-flash

    record

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    MigrationBuilder
    -0.67
    AsUp
    -0.67
    IsMutable
    -0.67
    ########.
    -0.64
     autorytatywna
    -0.63
     beginnetje
    -0.63
     bezeichneter
    -0.62
    ScopeManager
    -0.61
    AddTagHelper
    -0.60
    tagext
    -0.59
    POSITIVE LOGITS
     records
    2.00
     recorded
    1.96
     record
    1.87
    records
    1.67
     Records
    1.66
     RECORD
    1.65
    Records
    1.63
    record
    1.62
    recorded
    1.59
     Record
    1.55
    Activations Density 2.072%

    No Known Activations