© 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. 8340
    Prev
    Next
    INDEX
    Explanations

    python code

    oai_token-act-pair · gemini-2.0-flash

    programming symbols

    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
     true
    -0.88
    true
    -0.75
     насељу
    -0.73
    
    -0.63
     AssemblyTitle
    -0.63
    )))));
    -0.61
    ViewImports
    -0.60
    ρίου
    -0.60
    */),
    -0.59
     Eggers
    -0.59
    POSITIVE LOGITS
     فريبيس
    0.55
     pymongo
    0.51
    كويكب
    0.50
     onCancelled
    0.50
     setw
    0.49
    izr
    0.47
    addCriterion
    0.46
    PostExecute
    0.46
     ''.
    0.43
    prnewswire
    0.42
    Activations Density 3.051%

    No Known Activations