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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13798
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal language, organizations, and titles of works

    oai_token-act-pair · gemini-2.0-flash

    professional documents

    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
    NotBe
    -0.62
    Organisateur
    -0.61
     adipis
    -0.59
    الإنجليزية
    -0.56
    áfrica
    -0.55
     hinweg
    -0.55
    tvguidetime
    -0.54
    لكن
    -0.54
    Tính
    -0.53
    Diweddarwch
    -0.53
    POSITIVE LOGITS
     That
    1.11
     THAT
    0.83
     dat
    0.76
    That
    0.74
     To
    0.66
     For
    0.63
     che
    0.57
     thats
    0.57
    fileID
    0.53
    例句
    0.50
    Activations Density 6.007%

    No Known Activations