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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9864
    Prev
    Next
    INDEX
    Explanations

    math questions asking for the nth term or derivative in a sequence or equation

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     kasarigan
    -0.81
     оригіналу
    -0.66
     AssemblyCulture
    -0.65
    RenderAtEndOf
    -0.63
    )}</
    -0.59
    ttino
    -0.56
    )':
    -0.56
    orteur
    -0.55
    новниш
    -0.54
    లాలు
    -0.54
    POSITIVE LOGITS
     extérieures
    0.60
     étrangère
    0.57
     juridiques
    0.54
     vectorielles
    0.54
     linguistique
    0.53
     plastiques
    0.53
     financières
    0.53
     régulier
    0.52
     pédagogique
    0.52
     historiques
    0.52
    Activations Density 7.807%

    No Known Activations