© 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. 12633
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation separated by newlines

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
    ]='\
    -0.59
    ⁃
    -0.58
    ']='
    -0.57
     wondering
    -0.56
    ="'.$
    -0.56
     remembering
    -0.56
    '
    -0.56
    (')
    -0.56
    leun
    -0.55
     examining
    -0.55
    POSITIVE LOGITS
    تقاوى
    0.50
     neige
    0.49
     kaarangay
    0.48
     Meksiku
    0.47
     énergé
    0.46
     revés
    0.45
     تضيفلها
    0.45
    typeorm
    0.45
     étanche
    0.44
     dépos
    0.44
    Activations Density 9.125%

    No Known Activations