© 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. 3831
    Prev
    Next
    INDEX
    Explanations

    Greek characters and the parentheses that go with them

    oai_token-act-pair · gemini-2.0-flash

    Unusual symbols and characters

    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
    ρους
    -0.66
    ρων
    -0.57
     biaya
    -0.57
     Abonnez
    -0.55
    σουμε
    -0.54
     vostri
    -0.53
    νονται
    -0.53
    zeß
    -0.52
     trasporto
    -0.51
    ньої
    -0.51
    POSITIVE LOGITS
    ΑΙ
    0.68
    ΗΣ
    0.66
    EndInit
    0.64
    ευ
    0.64
    Décès
    0.64
    ΕΙ
    0.61
    ΕΣ
    0.58
    CppMethod
    0.57
    twimg
    0.56
    ΑΛ
    0.56
    Activations Density 2.303%

    No Known Activations