© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9145
    Prev
    Next
    INDEX
    Explanations

    words showing sequence or relationships, especially words connected by hyphens

    oai_token-act-pair · gemini-2.0-flash

    Prepositions and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     resourceCulture
    -0.90
    хьтан
    -0.61
    owiak
    -0.55
    tagext
    -0.54
    ագրություններ
    -0.54
    はじめに
    -0.49
    ftagPool
    -0.49
    MemoryWarning
    -0.49
     Mittag
    -0.47
     esterna
    -0.47
    POSITIVE LOGITS
    Begriffsklä
    0.64
    CloseOperation
    0.62
    LookAnd
    0.60
    jooq
    0.60
    zzleHttp
    0.56
    WriteAttribute
    0.55
     Sapi
    0.54
     ")");
    0.52
    <bos>
    0.51
    ValueStyle
    0.50
    Activations Density 1.463%

    No Known Activations