© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35444
    Prev
    Next
    INDEX
    Explanations

    fruits & vegetables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    進化
    0.43
     aggression
    0.41
    进化
    0.41
     Improving
    0.40
    améliorer
    0.40
    淩
    0.39
     संतुलन
    0.39
     assesses
    0.38
     improving
    0.38
     pioneering
    0.38
    POSITIVE LOGITS
    粵
    0.39
    Extraction
    0.39
    掲
    0.38
    炊
    0.37
    בע
    0.36
    Bathroom
    0.36
    झा
    0.35
    extraction
    0.35
    Majority
    0.35
     אין
    0.35
    Activations Density 0.009%

    No Known Activations