© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1372
    Prev
    Next
    INDEX
    Explanations

    words or phrases relating to academia, educational degrees, and academic study

    oai_token-act-pair · gemini-2.0-flash

    academic research

    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
     academic
    -2.13
     academics
    -1.93
    academic
    -1.92
     professor
    -1.83
     Academic
    -1.80
     Professor
    -1.78
    Academic
    -1.78
    Professor
    -1.70
     academia
    -1.68
     professors
    -1.63
    POSITIVE LOGITS
    LookAnd
    0.79
    AsUp
    0.74
     समीक्षाओं
    0.60
    sizeCache
    0.59
    tanleria
    0.56
     <=",
    0.55
    rawDesc
    0.54
    verifyException
    0.52
    xase
    0.51
    UnusedPrivate
    0.50
    Activations Density 1.557%

    No Known Activations