© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3151
    Prev
    Next
    INDEX
    Explanations

    javax.swing, jakarta.ws, mvc, db, fragment, appcompat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ate
    1.23
    places
    0.98
    ist
    0.97
    ot
    0.94
    ant
    0.92
    ともに
    0.88
    д
    0.87
    зки
    0.87
    र्गत
    0.87
    anen
    0.86
    POSITIVE LOGITS
     deviates
    1.05
    𝐧
    1.05
    Matches
    1.01
    𝐮
    1.00
     lows
    0.98
    koľ
    0.97
     ecosystem
    0.97
    ledged
    0.96
     lhs
    0.95
    vary
    0.95
    Activations Density 0.009%

    No Known Activations