© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6696
    Prev
    Next
    INDEX
    Explanations

    various common English words that appear frequently, and that often connect clauses or ideas.

    oai_token-act-pair · gemini-2.0-flash

    conversational text

    np_max-act-logits · 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
     we
    -3.06
    We
    -2.55
     We
    -2.53
    我们
    -2.09
    我們
    -2.08
     мы
    -1.94
     nous
    -1.88
     我们
    -1.86
     us
    -1.84
    we
    -1.82
    POSITIVE LOGITS
    ेशा
    0.57
     uns
    0.57
    Παραπομπές
    0.55
    canestro
    0.54
    évaluateur
    0.53
     saites
    0.50
     CreateTagHelper
    0.50
    ))[
    0.50
     وتسجيلات
    0.49
    localctx
    0.48
    Activations Density 4.152%

    No Known Activations