© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14632
    Prev
    Next
    INDEX
    Explanations

    a mix of different things, including the fragment "nu", French pronouns and determiners, Serbian pronouns and conjunctions, and the English pronoun "it"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RegistryLite
    -0.64
    Diwedd
    -0.54
     Portuguesa
    -0.54
     Públicas
    -0.53
    WebServlet
    -0.52
    richTextPanel
    -0.49
     Italij
    -0.48
    GeoNames
    -0.47
    ThroughAttribute
    -0.47
    ⓘ
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.82
    Билгалдахарш
    0.62
     <<<<<<<<<<<<<<
    0.59
     chi̍t
    0.55
    Шаг
    0.54
     BoxFit
    0.53
    plast
    0.52
    poons
    0.51
    værende
    0.50
     елның
    0.50
    Activations Density 0.563%

    No Known Activations