© 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. 6873
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to algorithms, math and computer science

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical texts

    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
     Normdatei
    -0.79
    XmlAccessType
    -0.72
    BeginContext
    -0.72
    httphttps
    -0.70
     برانيه
    -0.66
    ✭✭
    -0.63
     NUKAT
    -0.63
     sumpay
    -0.61
    NOPQRST
    -0.60
    TagMode
    -0.60
    POSITIVE LOGITS
    ViewFeatures
    0.67
     hjär
    0.53
    彼は
    0.48
     skall
    0.46
    彼女は
    0.45
     cifras
    0.44
     prezzi
    0.44
    xaml
    0.43
    Transferred
    0.43
    Scores
    0.42
    Activations Density 19.212%

    No Known Activations