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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3224
    Prev
    Next
    INDEX
    Explanations

    text about school grades, policy or academics

    oai_token-act-pair · gemini-2.0-flash

    academic/school performance

    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
    -0.94
     Academic
    -0.93
     ACADEM
    -0.89
    ACADEM
    -0.88
    academic
    -0.85
     academic
    -0.84
     academically
    -0.79
    ModelForm
    -0.75
    Academics
    -0.70
     GlobalKey
    -0.66
    POSITIVE LOGITS
    WriteTagHelper
    0.52
     sumpay
    0.50
    Бахар
    0.49
     שוליים
    0.49
    ftagPool
    0.47
    новништво
    0.45
    relativeTime
    0.44
    цездатний
    0.44
    Diwedd
    0.43
     HttpNotFound
    0.43
    Activations Density 3.976%

    No Known Activations