© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11596
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly relating to file handling and object properties

    oai_token-act-pair · gemini-2.0-flash

    programming terms or code structures

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

    code terms

    np_max-act-logits · gemini-2.0-flash

    say "▁"

    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_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
    WriteTagHelper
    -0.51
     Serikat
    -0.49
    urance
    -0.48
    [:]
    -0.43
    verti
    -0.42
     Grun
    -0.40
    ubus
    -0.40
     @__
    -0.39
     daly
    -0.39
    fore
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.88
     betweenstory
    0.73
     صوتيه
    0.70
    SharedCtor
    0.67
     MainAxisSize
    0.65
    randomUUID
    0.64
    SourceChecksum
    0.63
            
    0.63
    IntoConstraints
    0.62
    fromnode
    0.59
    Activations Density 0.772%

    No Known Activations