© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11348
    Prev
    Next
    INDEX
    Explanations

    words containing diacritics such as accent marks and the like

    oai_token-act-pair · gemini-2.0-flash

    Foreign/Unidentifiable 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
     È
    -0.50
     
    -0.49
    ʺ
    -0.47
    ★★★★★
    -0.46
    ¹
    -0.46
     referrerpolicy
    -0.44
     Â
    -0.44
    ="<?=$
    -0.44
     
    -0.44
     ´
    -0.43
    POSITIVE LOGITS
    ɚ
    0.65
    MemoryWarning
    0.62
    ʐ
    0.61
    ʁ
    0.58
     وتسجيلات
    0.57
    CloseOperation
    0.56
     виправивши
    0.56
    ɝ
    0.54
    ReusableCell
    0.54
    spesies
    0.54
    Activations Density 2.552%

    No Known Activations