© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7827
    Prev
    Next
    INDEX
    Explanations

    words that are prefixes or suffixes of chemical terms, Latin/Greek words, or other scientific terminology.

    oai_token-act-pair · gemini-2.0-flash

    scientific language

    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
    KURZBESCHREIBUNG
    -0.56
     getItemCount
    -0.52
    تقاوى
    -0.52
     المعيارى
    -0.51
    __':
    
    -0.50
    GEBURTSDATUM
    -0.50
    expandindo
    -0.49
     AspNetCore
    -0.48
     دیکھیے
    -0.47
    Хьажоргаш
    -0.47
    POSITIVE LOGITS
    za
    1.02
    sa
    1.01
    ka
    1.00
    ica
    0.94
    ita
    0.94
    va
    0.94
    ina
    0.93
    ika
    0.92
    ca
    0.91
    ja
    0.91
    Activations Density 3.199%

    No Known Activations