© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11436
    Prev
    Next
    INDEX
    Explanations

    acronyms and initialisms

    oai_token-act-pair · gemini-2.0-flash

    abbreviations and acronyms

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

    Abbreviations

    np_max-act-logits · gemini-2.0-flash

    acronyms

    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
     CreateTagHelper
    -1.04
    Билгалдахарш
    -0.99
     TextAppearance
    -0.94
    ThroughAttribute
    -0.93
    BufferException
    -0.92
     autorytatywna
    -0.90
    extAlignment
    -0.90
     disambiguazione
    -0.89
     يتيمه
    -0.88
     UnityEditor
    -0.88
    POSITIVE LOGITS
     
    1.02
     P
    0.69
    -
    0.62
     (
    0.60
     D
    0.59
     G
    0.57
     v
    0.57
     ex
    0.56
     f
    0.56
     R
    0.56
    Activations Density 6.602%

    No Known Activations