© 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-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178899
    Prev
    Next
    INDEX
    Explanations

    upset or surprise

    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_24_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
     immovable
    0.40
     brahman
    0.38
     変
    0.37
    Sched
    0.37
    फेल
    0.37
    টসম্যান
    0.37
     तत्
    0.36
     Paryayvachi
    0.35
    ✙
    0.35
     successors
    0.34
    POSITIVE LOGITS
    niają
    0.46
     นา
    0.43
     légende
    0.40
    简单
    0.39
    ucía
    0.39
    ้ำ
    0.39
    ética
    0.38
    increase
    0.38
     rie
    0.38
     চাষ
    0.38
    Activations Density 0.001%

    No Known Activations