© 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. 7935
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in internet forum posts, including slang and question answering.

    oai_token-act-pair · gemini-2.0-flash

    Social media posts

    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
     disambiguazione
    -0.82
     ujednoznacz
    -0.71
     bakgrund
    -0.67
     répondit
    -0.65
     StatelessWidget
    -0.63
     NUKAT
    -0.63
     skolan
    -0.59
     nė
    -0.57
     varandra
    -0.57
     aveug
    -0.56
    POSITIVE LOGITS
     i
    0.54
    setVerticalGroup
    0.53
     el
    0.50
     tích
    0.50
     tara
    0.50
     l
    0.49
    قدم
    0.49
     star
    0.48
     ecos
    0.48
     vista
    0.47
    Activations Density 20.857%

    No Known Activations