© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    words and characters common in French-language online forums, especially those discussing computer technical issues on operating systems

    oai_token-act-pair · gemini-2.0-flash

    French and Linux

    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
     θ
    -0.82
     α
    -0.80
     δ
    -0.73
     López
    -0.73
     Kō
    -0.73
     β
    -0.72
     García
    -0.72
     à
    -0.72
     À
    -0.71
     Ō
    -0.71
    POSITIVE LOGITS
     otomatig
    0.44
    reactstrap
    0.38
    mobileqq
    0.37
    Enllaces
    0.37
    DataAnnotations
    0.37
    ượt
    0.35
    oneofs
    0.33
    цездатний
    0.33
    DebuggerNonUser
    0.33
     alimentaires
    0.33
    Activations Density 7.630%

    No Known Activations